GleanMark Trademark Search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so description carries full burden. Discloses async execution, typical duration, processing handle return, and user notification. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is informative and well-structured, though slightly wordy. Front-loads purpose and async detail. Could be trimmed but effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers async workflow, analysis content, and next step call. Lacks output schema details but compensates with status tool reference. Adequate for complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter (serial_number) with full schema coverage. Description does not add parameter-specific meaning beyond schema, but coverage is 100%, meeting baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it analyzes full prosecution history with narrative timeline and examiner behavior patterns. Distinguishes from siblings like get_prosecution_timeline and get_mark_prosecution_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states async nature for authenticated users and instructs to call get_prosecution_history_status for results. Lacks explicit instructions on when not to use. Context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses key behaviors: asynchronous execution (1-2 minutes), return of a processing handle, and the need to call get_ttab_proceeding_analysis_status. It also mentions the quick_mode parameter's effect. However, it does not cover error handling, authentication requirements, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no wasted words. It is front-loaded with the core purpose, then adds the async behavior detail, and finally instructs the user. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description adequately covers the tool's complexity: purpose, async workflow, and quick mode. It summarizes output as a structured summary with timeline, positions, and assessment. Missing are details on error responses or input validation, but overall it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. The description adds no additional meaning beyond what the schema provides; it mentions quick_mode's effect ('skips lower-priority documents') which is already described in the schema. The purpose is reiterated but does not enrich parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: analyze a TTAB proceeding in depth by fetching documents, identifying key arguments, and returning a structured summary with timeline, party positions, and strategic assessment. This distinguishes it from sibling tools like get_ttab_proceeding_details which likely only retrieve details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains that for authenticated full-mode runs the tool is asynchronous and requires calling a status endpoint, but it does not explicitly state when to use this tool versus alternatives like get_ttab_proceeding_details or search_ttab_proceedings. Guidance on when-not to use is absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description partially informs behavior: it's quick, combines domain and trademark checks, and outputs recommendation tiers. However, lacks details on data sources, failure modes, or destructive nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that are front-loaded with purpose, no filler. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description adequately conveys purpose and usage for a quick initial check. Could elaborate on how parameters affect results, but sufficient for most agents.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are documented. Description adds minimal context beyond schema, e.g., combining domain and trademark. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it checks brand availability by combining domain and trademark signals, and returns a recommendation tier. It distinguishes from sibling tools like check_domain_availability and full clearance searches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly described as a 'good first step before a full clearance search,' guiding when to use. Does not specify when not to use, but context is clear given sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries the burden. Mentions return value categories (available, parked, commercially used, taken) and additional .com variations, but does not disclose whether the operation is read-only, authentication requirements, or rate limits. Adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences. First sentence states the primary action; second explains what is returned. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description partially compensates by listing status categories. However, it lacks details on output format, error conditions, or when to use each status. For a simple tool this is minimally viable but leaves room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Both parameters (brand_name, tlds) are already described in the schema. The description adds no additional semantic nuance beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool checks domain availability for a brand name across TLDs, and distinguishes from sibling tools like check_brand_availability (trademark) by focusing on domain name status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus siblings such as check_brand_availability or web_research. The description does not mention alternatives or conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the tool returns similarity scores and risk assessment, but does not mention if it modifies data, needs authentication, or has rate limits. The lack of explicit read-only hint or side effect disclosure is a gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, highly concise, front-loaded with verb and resource. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Parameters are fully documented in schema, output schema exists (though not shown), and description covers core purpose. Could mention that Nice classes are used for overlap analysis, but the schema already does that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no extra semantic detail beyond the schema, meeting baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool compares two trademarks for likelihood of confusion using DuPont-style analysis, and distinguishes it from siblings like 'get_similar_marks' which likely finds similar marks rather than compares two specific ones.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (comparing two specific marks), but does not provide explicit guidance on when not to use or alternatives like 'run_knockout_search' or 'run_safe_analytics'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'count and preview' implying read-only behavior, but does not specify whether it is destructive, requires authentication, rate limits, or what 'metadata coverage' entails. The description lacks explicit behavioral traits beyond the basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with three sentences that front-load the main purpose and then provide usage guidelines. Every sentence adds value, and there is no extraneous content. It is well-structured and easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (9 parameters, no output schema), the description explains what the tool does and what attributes are involved, but lacks details on the output format (e.g., does it return a single count, a breakdown, or a preview list?). It mentions 'metadata coverage' but does not define it. The description is adequate but could be more complete regarding return structure and data scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 9 parameters and only 44% schema description coverage, the tool description provides high-level categories (mark-type, standard-character, Nice-class, status, color intersection) that help interpret the parameters. However, it does not describe each parameter individually, leaving many (like limit, mark_types, nice_classes, class_match_mode, color_match_mode, standard_characters) without additional context. The description adds value but is not comprehensive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool counts and previews USPTO marks by record attributes like mark-type, standard-character, and Nice-class, distinguishing from owner identity and sibling tools like search_by_owner. It specifies the exact attributes (drawing type, standard-character, Nice-class, status, cross-attribute) and explicitly excludes color-only counts, rankings, lists, vocabulary, or single-mark color claims.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: use for mark-attribute counts (drawing type, standard-character, Nice-class, status, cross-attribute), do not use for color-only counts (use search_claimed_colors instead), and do not use run_safe_analytics for these counts. This clearly indicates when to use and when not to use the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description is the sole source. It briefly indicates a read operation (look up) but lacks details on authorization, rate limits, or return format. Adequate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the key action and resource, no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple lookup tool without output schema, the description is functional but could explain return structure or relationship to other class tools. Missing some completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 4 parameters. The description adds little beyond restating the purpose ('coordinated or related'), so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool looks up coordinated or related Nice classes for a given class number, using precise verbs and differentiating from sibling tools like get_nice_classes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or alternatives guidance is provided. The description implies usage for class relationship lookup but does not clarify when to choose coordinated vs related, nor any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description discloses sampling behavior, truncation notification, and return fields (avg/median/percentiles, missing start event counts, example marks). Sufficient for read-only aggregation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is 5 sentences, front-loaded with purpose. Each sentence adds value. Could be slightly more structured but is efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and 9 parameters, description covers core functionality well. Lacks explicit output format details but provides sufficient context for an AI agent to understand what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds meaning by explaining cohort logic, preset events, wildcard usage for raw codes, and date window constraints, going beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'Aggregate event-to-event pendency' and resource 'COHORT of marks', with an example. Distinguishes from siblings like get_mark_prosecution_summary by focusing on interval analytics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance on cohort selection, date window, and interval events. Recommends using get_event_code_reference for non-preset codes. Lacks explicit 'when not to use', but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description discloses key behavioral traits: sorting by prosecution history length, inclusion of event counts and office action flags. With no annotations, the description carries the full burden and adequately conveys the read-only nature and output structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three front-loaded sentences: purpose, behavior, and when to use. Every sentence earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so description must explain return values. It does so by mentioning event counts, office action flags, and sorting. With 7 parameters and no required ones, the description and schema together provide sufficient context for agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description adds value beyond schema by clarifying aliases (e.g., correspondent_id for canonical_correspondent_id) and providing practical usage examples (e.g., 'Use 90 for last 3 months' for recent_window_days).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly specifies verb 'Get', resource 'trademarks', and the filtering by attorney/correspondent. It also lists included data (event counts, office action flags) and sorting behavior, distinguishing it from siblings like run_analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly recommends using this tool instead of run_analysis for attorney-specific queries. Additionally, parameter descriptions provide guidance on when to use aliases (e.g., correspondent_name preferred when caller knows it's a correspondent name).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds that the widget contains the full profile and to keep prose concise, which provides operational guidance but doesn't disclose additional behavioral traits like data freshness or authentication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences and front-loaded with the core purpose. It is concise but could be slightly more streamlined by removing the redundant 'Do not answer from general knowledge' clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description doesn't need to detail return values. It covers the main use case and invocation context. The tool's parameters are all optional, and the description provides enough guidance for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description mentions 'top clients' and 'top Nice classes' which relate to top_client_limit and top_class_limit parameters, adding some context beyond the schema. However, it doesn't explain url_key vs search_term resolution logic.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool summarizes a correspondent's specialization including top clients, Nice classes, and prosecution vs TTAB profile. It distinguishes from sibling tools like get_correspondent_marks or get_firm_top_correspondents by focusing on specialization profiling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly says 'Use this when the user asks what a specific correspondent or attorney specializes in' and gives a prohibition against using general knowledge. It doesn't list alternatives but provides sufficient context for when to invoke.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the burden. It indicates a read-only lookup operation, but does not disclose any behavioral traits such as data freshness, rate limits, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that is front-loaded with the action and resource, containing no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks details about the output format (e.g., boolean, mapping, or structured result). Given there is no output schema, the agent would not know what to expect from the tool's response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and already explains both parameters. The description adds value by listing concrete examples of deadline types (e.g., office action response, Section 8), which complements the enum values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Check' and the specific resource 'USPTO event code' against a 'deadline type', which directly distinguishes it from sibling tools like get_event_code_reference or get_mark_deadlines.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for checking satisfaction of a deadline type, which is clear for the specific use case. However, it does not explicitly state when not to use it or suggest alternatives among the many sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses return fields (code, description, category) but lacks details on side effects, authentication, rate limits, or data source. Since no annotations are provided, the description carries the full burden and is only moderately transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundancy. The first sentence states the purpose, the second elaborates on search methods and output. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description explains return fields (code, description, category). It covers essential usage scenarios and is consistent with sibling tools. Missing error handling or pagination details, but completeness is high for a simple lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds context by mentioning search methods (exact code, prefix, keyword) but does not significantly enhance understanding beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'look up' and resource 'USPTO event codes used in trademark prosecution.' It clearly distinguishes from sibling tools like 'get_event_status_mapping' by focusing on reference lookup via code or keyword.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly indicates use when needing to decode event codes, but it does not explicitly state when to avoid it or mention alternatives among sibling tools such as 'get_event_status_mapping'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so description must carry full burden. It only mentions a read operation but does not disclose rate limits, required permissions, output structure, or any side effects. Minimal insight into behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words. Front-loaded with the action and object. Efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Simple tool with two parameters. Description covers purpose but does not explain what the output looks like (e.g., list of mappings with frequencies) despite lacking an output schema. Adequate but could be richer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description adds no extra semantics beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it looks up the most common status code and definition following a specific prosecution event code. The verb 'look up' and resource are specific, but does not explicitly distinguish from sibling 'get_event_code_reference' which might have overlap.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like get_event_code_reference or research_office_action. No contextual usage hints provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries full burden. It discloses what the tool returns (fame tier, path, etc.) and its limitation (circumstantial signal). For a read-only data retrieval tool, this is sufficient. No side effects or auth needs mentioned, but not required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one dense paragraph but front-loads the main output categories and then the usage context. Every sentence adds value, but it could be broken into bullet points for clarity. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description comprehensively lists all components returned (fame tier, path, class footprint, etc.) and explains the tool's purpose and limitation. Given only one parameter and no nested objects, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of parameters, so baseline is 3. The description for the parameter 'mark_or_stem' matches the schema description exactly, adding no extra value. The tool-level description does not provide additional semantic details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the tool gets the full fame profile for a brand, listing specific components like fame tier, path, class footprint, etc. It distinguishes from the sibling tool 'is_mark_famous' which likely provides a simpler boolean. The verb 'get' and resource 'fame profile' are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states when to use: to explain why a mark is famous or to profile a senior mark before legal strategies. It also warns that it is circumstantial, not statutory proof. However, it does not explicitly mention alternatives like 'is_mark_famous' when a simpler check is needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It explains the tool combines deadlines and OAs from two sources (case-file events and prosecution documents), includes special indicators, and mentions time windows. However, it does not disclose error handling, rate limits, or behavior when firm is not found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that front-load the core functionality and then provide usage examples. No redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately describes the return values (deadlines, recent OAs, indicators) and the time frames. It covers the tool's scope sufficiently for a 4-parameter tool without nested objects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description does not add meaning beyond the schema's parameter descriptions; it merely restates the purpose without enriching parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verbs ('Resolve', 'return') and clearly states the resource ('law firm') and what it returns (overdue/next-window deadlines, recent Office Actions, with indicators). It distinguishes from sibling tools like get_firm_deadlines and get_firm_oa_outcomes by combining both and including ROA-filed and §2(d) indicators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use this first for questions like...' and provides example queries. Does not mention when not to use or alternatives, but the guidance is clear for the intended use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the data scope (public, system-generated) and what is not included, but does not mention authentication requirements, rate limits, or other behavioral aspects. Adequate but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two sentences with no redundant information. Every sentence adds value: stating the purpose and clarifying constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 7 parameters and an output schema, the description covers the essential purpose and constraints. It does not explain the output format, but the presence of an output schema mitigates this. Slightly more detail on use cases would elevate completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are well-documented in the schema. The description adds no additional parameter-level detail beyond the schema. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets public, system-generated trademark deadlines for a law firm, and explicitly lists what it does not expose (workspace, client, reminder, user-created data). This distinguishes it from sibling tools like get_mark_deadlines or get_owner_deadlines.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains it uses only public firm resolution and prosecution mappings, implying use for firm-level public data. It also states what is not exposed, guiding against using it for private data. However, it does not explicitly mention alternative tools for different needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description discloses key behaviors: it resolves firms, computes rates both raw and excluding pending matters. This adds sufficient transparency beyond what annotations could provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the action, and contains no unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what rates are computed and the filtering. Although no output schema exists, the description sufficiently outlines the tool's purpose for a simple analytical tool. Minor lack of detail on output format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description does not add significant extra meaning beyond the schema definitions for firm_name and limit. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool resolves a firm and computes OA outcome rates, with specific examples of questions it answers. It distinguishes from sibling tools that focus on different firm-related tasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this for questions like...' providing clear context for when to use. It does not mention when not to use or alternatives, but the examples are sufficient for guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses that the tool returns a ranked list with filing volume, prosecution, and TTAB activity counts, implying read-only behavior. No contradictions, but could mention auth or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, then usage guidance, then output instruction. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and parameters are simple, the description covers the purpose, ranking criteria, and usage context (widget integration). Complete for a list retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds no extra meaning beyond the schema descriptions (firm_name and limit). Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves leading correspondents or attorneys at a named law firm, ranked by filing volume with prosecution and TTAB activity counts. The verb 'Get' and specific resource 'leading correspondents or attorneys inside one named law firm' differentiate it from sibling tools like get_firm_correspondent_tasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool (e.g., user asks for top correspondents at a specific firm) with an example query. It also advises calling the tool immediately and keeping prose to the main takeaway. However, it lacks explicit when-not-to-use or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must bear the full burden. It discloses that the tool returns the latest office action, latest response, and parsed refusal grounds, but does not mention any behavioral traits such as rate limits, permissions, or whether it modifies data. For a read-only retrieval tool, the description is adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences. The first sentence covers the core functionality, and the second provides a crucial usage guideline. Every sentence adds value with no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the single parameter and no output schema, the description reasonably explains what the tool returns (latest OA, response, refusal grounds). It specifies that refusal grounds are 'VERIFIED' and parsed from OA text. While it could detail the format or link to sibling tools, it is sufficient for an agent to understand the tool's purpose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter (serial_number) with 100% schema description coverage. The description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets the latest office action, response, and parsed refusal grounds for a trademark serial number. It specifically instructs the agent to use refusal_grounds as authoritative, distinguishing it from sibling tools like research_office_action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear directive: 'Use refusal_grounds as the authoritative answer... never infer from the document title or general knowledge.' This guides the agent on how to interpret the output. However, it does not explicitly specify when to choose this tool over siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It transparently lists what the summary covers (mark details, goods/services, status, owner, prosecution, legal proceedings). However, it does not disclose any limitations, permissions, or rate limits, but for a read-only summary, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the main action ('Get an AI-generated deep-dive summary') and lists covered elements. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately lists what the summary covers. For a simple one-parameter lookup tool, this is complete. Minor improvement could include what format or level of detail to expect, but not strictly necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter described as 'USPTO serial number'. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns an AI-generated deep-dive summary of a specific trademark, listing covered aspects. It distinguishes from siblings like get_mark_prosecution_summary (which focuses on prosecution) and get_owner_ai_summary (which is owner-level).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a comprehensive AI summary is needed, but provides no explicit when-to-use, when-not-to-use, or alternative tools. For example, it doesn't mention that for prosecution-only needs, analyze_prosecution_history might be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It correctly discloses that only system-generated deadlines are returned and that name resolution occurs. However, it omits details on pagination, rate limits, or error conditions, which would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence states the core function, and the second adds critical scope boundaries (exclusion of user data). Every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters, full schema documentation, and an output schema, the description is sufficient. It highlights the key differentiator from sibling deadline tools. Minor omission: does not mention that deadlines are time-bounded by parameters, but schema covers that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The description adds value by explaining the resolution between serial_number and subject_name, and clarifies that include_opposition_period is deprecated. This enhances the agent's understanding beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves 'public, system-generated trademark deadlines' for a specific mark, with explicit mention of resolution from mark name to serial. This distinguishes it from sibling tools like get_owner_deadlines or get_firm_deadlines which handle user-created deadlines.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly excludes user-created deadline data, signaling when not to use this tool. It implies usage for public deadlines and mentions resolution logic, but does not name specific alternative tools for workspace or client deadlines.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries the burden. It discloses that data comes from USPTO records and not live WIPO/EUIPO, and lists what information is retrieved. It doesn't mention read-only nature or error cases, but the disclosure is sufficient for its purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: first sentence lists what it retrieves, second gives usage guidance. It is well-structured, concise, and front-loaded with the most important information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has low complexity (1 param, no output schema). The description covers the purpose, usage context, data source limitation, and lists key fields returned. It does not detail return format or errors, but for a simple lookup tool it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with only one parameter 'serial_number' described as 'USPTO serial number'. The description adds context by specifying it's for U.S. trademarks but does not add formatting or constraints beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves international/foreign footprint of a U.S. trademark, listing specific data points like IR number, date, status, etc. It distinguishes from siblings by focusing on international aspects, not overlapping with other tools like 'get_fame_profile'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this for ANY question about a mark's foreign, international, Madrid Protocol, WIPO, or EUIPO registrations' and notes data source limitation (USPTO only). It does not explicitly exclude alternatives or provide when-not-to-use scenarios, but the guidance is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description implies read-only live data fetch and mentions ranking. It is transparent about what it does but could be more explicit about side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with core purpose, then usage guidance. Every sentence adds value, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 params, output schema exists, no annotations), the description fully informs the agent on when and how to use the tool, including behavioral expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters have schema descriptions (100% coverage), so description adds minimal extra meaning beyond explaining overall purpose. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool shows which owners hold marks matching a term and summarizes their broader portfolios. It distinguishes from sibling 'run_safe_analytics' by name and use case.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises to use this tool first for owner-landscape questions, provides example queries, and recommends calling immediately instead of relying on general knowledge.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description should disclose behavioral traits. It only lists output fields but does not state read-only nature, side effects, authentication requirements, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences: first states purpose, second details output. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool, the description covers core functionality but lacks detail on the response format (e.g., what 'compact' means, structure of milestones). With no output schema, more specificity would help.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the parameter 'serial_number' is already described by its schema. The description adds no additional meaning beyond 'USPTO serial number', so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a 'compact prosecution summary' for a trademark serial number, listing specific return contents (status, document counts, dates, milestones, latest key event). This distinguishes it from siblings like get_prosecution_timeline or get_mark_ai_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives. There are no explicit when/when-not criteria or references to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention that the operation is read-only, that no changes are made, or any potential rate limits or data source specifics. The description is silent on these aspects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short, front-loaded sentences with no fluff. Every sentence adds value, stating the main purpose and the two modes of operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description need not explain return values. It covers the two main use cases (lookup and search), which is adequate for a simple read tool. Minor omission: does not hint at the type of information returned (e.g., class titles), but output schema compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters well. The description adds minimal context by linking parameters to usage modes ('lookup specific class numbers or search for classes by keyword'), but does not significantly enhance understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves information about Nice Classification classes for trademark registration, with two modes: lookup by class numbers and search by keyword. This is a specific verb-resource combination that distinguishes it from siblings like recommend_nice_classes and get_class_relationships.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage scenarios (lookup vs search) but does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites. For example, it doesn't mention that recommend_nice_classes is preferable for suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries the burden. It mentions results are cached for 30 days, which is useful. However, it does not disclose whether the tool is read-only, any authentication or cost implications, or how it behaves if the owner is not found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states the purpose, second lists coverage areas and caching behavior. No wasted words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), the description adequately covers what the analysis includes and caching. It could mention the output format (e.g., text) but this is not essential. The parameter description partially addresses prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the single parameter is described in the schema with format and usage hint). The tool description does not add additional parameter semantics beyond what the schema already provides. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides an AI-generated strategic analysis of a trademark owner, listing specific aspects covered (brand protection, litigation posture, etc.). It distinguishes itself from siblings like get_mark_ai_summary (which focuses on a single mark) and get_owner_filing_trends (which is more specific).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for strategic owner analysis. The parameter description recommends using search_by_owner first to get the correct normalized name. However, it does not explicitly state when to use this tool versus alternatives like get_owner_filing_trends or get_owner_ttab_enforcement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the tool is read-only (public data, system-generated), uses external resolution, and excludes internal data. It doesn't mention idempotency or rate limits, but for a read operation this is sufficient transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences. First sentence states purpose, second clarifies scope and exclusions. No redundancy, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters and output schema present, the description adequately explains what data is included and excluded. It doesn't detail return structure, but output schema likely covers that. Slightly above minimum due to thorough scope clarity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with all parameters described. The description adds general context but no specific parameter semantics beyond the schema. Baseline 3 is appropriate; no extra value added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'Get', resource 'deadlines', and scope 'across a specific owner’s marks'. It distinguishes from siblings like 'get_mark_deadlines' (single mark) and 'get_firm_deadlines' (firm-level) by emphasizing public, system-generated data and excluding workspace/client data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explains what the tool uses (public USPTO owner resolution) and explicitly states what it does NOT expose (workspace, client, reminder, user-created deadlines). This provides clear context for when to use (public deadlines) and when not to (if internal data is needed), though it lacks explicit alternative naming.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the output (yearly counts by class) and hints at portfolio evolution, but does not specify behavior for edge cases (e.g., missing data, time range handling beyond defaults) or any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, front-loads the core purpose, and contains no redundant information. Every word is meaningful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (3 parameters, all documented) and absence of output schema, the description provides enough context: it explains what is returned (yearly counts by class) and includes a usage hint. It could mention the output format more explicitly, but it's largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value beyond the schema by advising to use search_by_owner first. This helps the agent understand the correct usage of the owner_name parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get', the resource 'trademark owner's filing trends', and specifies it provides yearly filing counts broken down by Nice class. This distinguishes it from siblings like get_top_filers or get_owner_ai_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description itself does not explicitly state when to use this tool vs alternatives, but the parameter description for owner_name gives a crucial guideline: 'Use search_by_owner first to find the exact name.' This implies a prerequisite step, which aids correct usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose all behavioral traits. It only states 'most frequent keywords' but does not specify the source, limits on classes, registration status, or whether it returns raw counts. This leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise—two sentences that immediately convey the tool's purpose and value. Every sentence adds useful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should indicate the return format. It mentions 'shows keywords' but does not specify whether results include frequencies or counts. For a simple keyword tool, this may be adequate but lacks completeness for an agent expecting structured output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters have descriptive schema comments (100% coverage). The description adds value by explaining the limit's purpose and instructing to search_by_owner first for owner_name. This goes beyond bare parameter definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the most frequent goods/services keywords for a trademark owner, with a specific verb 'Get' and resource. It explains the utility for brand strategy and class patterns, distinguishing it from sibling tools like get_owner_filing_trends.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for understanding an owner's focus areas and class patterns. The parameter description for owner_name instructs to use search_by_owner first, providing a clear prerequisite. However, it lacks explicit exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description bears full burden. It discloses filtering logic, separate reporting of targets, and a limitation (claimed-color metadata does not prove pleading). This is good transparency, though more detail on return structure could help.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with two paragraphs, front-loading the main purpose. It is slightly verbose but every sentence adds information. Could be condensed slightly without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 parameters, high complexity, and no output schema, the description covers filtering, limits, and cross-tool references. Missing output format details, but overall sufficiently complete for an intelligent agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 77% (high), baseline 3. The description adds meaning beyond schema, e.g., clarifying the claim-color limitation and the behavior of target_class_match. This adds value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it analyzes one trademark owner's TTAB enforcement, with specific filtering and counting behavior. It distinguishes from sibling tools like analyze_ttab_proceeding by noting where to find evidence of color allegations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use this tool vs analyze_ttab_proceeding for color evidence. It also highlights support for exact class-only queries via target_class_match=only. No explicit when-not, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the compact nature, includes a warning about misinterpretation of total records vs. initiated oppositions, but does not address authentication or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences front-load the purpose, include a behavioral warning, and an alternative tool—no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives sufficient context about the return value (breakdowns and warning), but lacks details on how the limit parameter affects output or pagination, which would be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67% (below 80%), and the description adds no additional meaning to the parameters. It does not clarify the year or limit parameters beyond what the schema provides, and limit lacks a schema description entirely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a compact TTAB history for one owner with specific breakdowns (inter partes, opposition, cancellation, etc.), and distinguishes it from sibling tools by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises when to use this tool (for compact history) and when not, directing users to get_owner_ttab_enforcement for alternative analysis.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must supply all behavioral context. It indicates a read operation and lists return fields, but does not disclose potential side effects, authentication needs, or limitations such as document availability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no fluff, front-loaded with purpose, and efficient in conveying essential use information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters and no output schema, the description covers the core retrieval logic and special case for text_query. Missing details on max_chars and return structure, but overall sufficient for an agent to understand usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 86% schema coverage, the description adds value beyond the schema by explaining when to use text_query and clarifying that document_id is the preferred selector from list_prosecution_documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Retrieve one specific USPTO prosecution document'), identifies the tool as a singular document retrieval tool, and distinguishes it from list_prosecution_documents by referencing the stable document_id from that list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance for using text_query when the user asks about a particular issue, implying when to use this parameter. However, lacks explicit when-not-to-use or differentiation from sibling tools like analyz_prosecution_history.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that it returns raw data without AI analysis, which is behavioral. However, it does not mention any side effects, authentication needs, rate limits, or data range/pagination. Without annotations, more detail would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly packed sentence that efficiently conveys the purpose, content, and nature of the data. It is front-loaded and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one parameter, no output schema, and no annotations, the description provides sufficient context by listing the types of events included. It could mention more about the format or coverage, but it is largely complete for a straightforward retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the single parameter 'serial_number' with a description 'USPTO serial number', so schema coverage is 100%. The tool description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get', the resource 'prosecution timeline for a trademark', and specifies the content as a chronological list of office actions, responses, and key events. It differentiates itself from sibling tools by noting 'Raw data without AI analysis'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining raw timeline data, but it does not explicitly state when to use this tool versus alternatives like 'analyze_prosecution_history' or 'get_mark_prosecution_summary'. No exclusions or when-not guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention whether the tool is read-only, idempotent, or has any side effects. While a lookup is likely safe, the description fails to explicitly state behavioral traits beyond listing what can be looked up.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently states the tool's purpose. It is concise but could be more structured with bullet points or a clearer separation of concepts. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, no output schema) and many sibling tools, the description covers its scope adequately but lacks completeness. It does not describe the output format, pagination, or behavior when no results are found. For a lookup tool with no output schema, more detail on return values would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds context by specifying that it covers 'small lookup tables' and lists examples, but this largely overlaps with the schema enum. Overall, it provides minimal additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the verb 'look up' and the resource: 'USPTO or TTAB reference codes and small lookup tables'. It lists many example reference types, distinguishing it from more specific sibling tools like get_nice_classes or get_event_code_reference by being a generic lookup for multiple small tables.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternative sibling tools. It implies usage by enumerating the reference types, but lacks guidance on when to use this generic lookup versus a more specific tool like get_nice_classes. No exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the matching methods and two output scores but omits details like data freshness, pagination behavior, or any restrictions. The behavioral disclosure is adequate for a search tool but could be more thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with front-loaded purpose. Every sentence adds essential information: purpose, method, and return value explanation. No wasted words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with 4 parameters and an existing output schema (not shown but referenced), the description covers the core semantics. It names the two scores which is critical for interpreting results. Slight lack of guidance on using scores for decision-making, but overall complete given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds a small hint about 'nice_classes' ('similar marks in same classes are higher risk') which is already implied in the schema's description. No substantial additional meaning beyond the schema is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Find', the resource 'USPTO trademarks similar to a given mark name', and specifies the method used (examiner-style knockout search with phonetic, trigram, and component matching). It distinctly positions the tool for trademark clearance searches, differentiating it from siblings like 'phonetic_search' or 'run_knockout_search'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description tags the tool as 'useful for trademark clearance searches', providing context but no explicit guidance on when not to use it or alternatives among 50+ sibling tools. The agent gets some usage context but lacks decision support for choosing between similar tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the widget already contains the ranking, hinting at low latency, but does not disclose any side effects, permissions, rate limits, or error conditions. Lacks transparency for what happens with no results or missing parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three well-structured sentences. The first sentence gives purpose and parameters, the second gives usage guidance, and the third reinforces immediate tool use. No redundant or superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a full output schema and 100% parameter coverage, the description provides sufficient context for typical usage. It explains when to call the tool and to avoid general knowledge. It could mention handling of empty results or date format specifics, but overall complete given the structured schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents each parameter. The description adds minimal value beyond summarizing the filter types (date, filer type, Nice classes). It does not provide additional meaning or examples beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a ranked filer table with specific filters (date range, filer type, Nice classes). It explicitly distinguishes from siblings by listing use cases like top owners, law firms, or correspondents, and contrasts with general knowledge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit context for when to use (user asks for top filers by class/date). Includes example prompts and advises against using general knowledge. Does not mention when not to use or list alternatives, but the sibling context is implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure but is minimal. It does not mention rate limits, authentication, response format, or what constitutes an aggregate statistic. The agent gets no cues about side effects or data freshness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently communicates the tool's purpose. No words are wasted, though additional detail could improve clarity without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 parameters, no output schema, and heavy sibling competition, the description is insufficient. It omits details about return structure, date handling, grouping behavior, and the difference between metric types. The agent would struggle to use this tool correctly without external knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (3 of 6 parameters have descriptions). The tool description does not elaborate on any parameter, leaving undocumented parameters like group_by, nice_class, and time_period unexplained. Some value is added by the schema's enum constraints, but the description fails to compensate for the gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves aggregate statistics about USPTO filings, registrations, and TTAB proceedings, matching the metric enum values. It effectively communicates the resource and scope, though it could differentiate more from sibling tools like get_top_filers or count_trademarks_by_attributes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus siblings such as get_top_filers or search_trademarks. The description lacks indications of prerequisites, typical use cases, or excluded scenarios, leaving the agent to infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries full burden. It discloses the output: metadata, viewer link, PDF link, status, text, and excerpts. It does not mention error behavior or side effects, but is fairly detailed about what the tool returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences covering purpose, output, and usage guideline with no redundant language. Every sentence is necessary and impactful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a retrieval tool with no output schema, the description lists return fields and provides usage alternative. It lacks explicit mention of error cases or single-document guarantee, but overall is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% (3 of 4 parameters have descriptions). The description adds context that text_query returns excerpts, but does not elaborate on max_chars beyond the schema's constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves and reads a specific TTABVUE filing by proceeding number and entry number, explicitly distinguishing it from sibling tool get_ttab_proceeding_details which is used when entry number is unknown.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs to use get_ttab_proceeding_details first when the entry number is unknown, providing a clear alternative and usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided. The description discloses the data returned (parties, marks, counsel, recent filings with entry numbers and links) and implies a safe read operation. However, it does not explicitly state that the tool is read-only or mention any side effects, which would be useful for full transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at three sentences, with the primary purpose front-loaded and the alternatives listed succinctly. Every sentence serves a purpose without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), the description is complete. It explains what the tool returns, includes usage guidance, and specifies the single required parameter. No gaps remain for an agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter with 100% schema description coverage. The description does not add any additional meaning beyond the schema's description of the proceeding number and example. The baseline score of 3 is appropriate since the schema already documents the parameter sufficiently.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'raw details for a TTAB proceeding', listing specific components (parties, marks, counsel, recent filings). It distinguishes from siblings by naming alternative tools for other use cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit usage guidance is provided: 'Use get_ttab_document to read one selected filing. Use get_owner_ttab_enforcement for owner-wide distributions and analyze_ttab_proceeding for AI-powered merits analysis.' This tells the agent when to use alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully explains behavioral traits: market-specific fame determined by Nice class proxy, returns specific fields, and is circumstantial. It does not mention authentication or error behavior, but covers key behavioral aspects with legal context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is a single focused paragraph with no wasted sentences. It front-loads the purpose, then explains key nuances and use cases, all within 6 sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description enumerates return fields (is_famous, famous_in_class, etc.) and covers caveats. It is complete for the tool's complexity and supported by sibling tools that handle other trademark aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description adds context such as example mark values and explains the class parameter as a market proxy. It reinforces the schema's meaning without being redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool checks if a trademark is famous for a specific market, uses a precise verb 'Check whether', and distinguishes it from other trademark tools by focusing on fame. It provides specific use cases and legal references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explicitly lists use cases like 'is X famous for <goods>?' and mentions legal contexts (cited in §2(d) and §43(c)). It notes the tool is a circumstantial signal, not statutory proof, guiding appropriate use. However, it does not explicitly mention when not to use or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the burden of disclosing behavior. It mentions output elements like identifiers, links, and status but does not confirm whether the operation is read-only or if any side effects occur. The absence of annotations and explicit safety guarantees leaves some uncertainty, though the list operation implies a safe read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the primary action. It is concise but includes necessary detail about document types. Minor improvement could be trimming less essential examples, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The lack of an output schema increases the need for description completeness. The description lists included document attributes but does not specify return format (e.g., array, pagination), sorting, or default behavior for empty results. It also does not mention sibling tools for analysis, but does reference the reading tool. Some gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (both parameters have descriptions). The tool description adds minimal parameter-specific value beyond what the schema already provides, such as listing document types but not parameter formatting. With high coverage, a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List'), the resource ('prosecution documents'), and the scope ('for a trademark serial number'). It enumerates what is included (stable document identifiers, working USPTO links, extraction/readability status, etc.), effectively distinguishing it from the sibling tool 'get_prosecution_document' which reads a single document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly directs users to 'Use get_prosecution_document to read one selected document,' providing a clear when-to-use alternative. However, it does not address other potential alternatives like 'analyze_prosecution_history' for analysis, missing some context for broader decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the tool is a read operation and highlights the correspondent field, but lacks details on authorization, rate limits, or other behavioral traits. The information is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences front-loading the purpose and key details, with zero wasted words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 1-parameter tool with an output schema, the description covers the essential return fields and adds a specific use-case hint. 'And more' is acceptable given the output schema fills in the rest, making it nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with the serial_number parameter fully described. The description does not add new semantic meaning beyond the schema, but reinforces its purpose. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves detailed information about a USPTO trademark by serial number, listing specific fields like owner, status, and correspondent. It distinguishes from siblings by focusing on a single trademark lookup, but doesn't explicitly contrast with other search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a specific use case: 'use this for which firm represents/is correspondent for questions', providing partial guidance. However, it does not mention when not to use or list alternative tools for similar purposes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries full burden. It discloses the algorithm (Metaphone+trigram), whole-mark threshold, and limitations. It clearly states what the tool does NOT do (cannot support clearance conclusions). However, it does not mention any side effects or auth requirements, but for a search tool this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph that packs essential warnings and usage notes without being verbose. It could benefit from bullet points or structured sections, but it remains concise and front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and no annotations, the description focuses on core functionality and limitations but omits parameter details and return value format. The output schema exists but is not referenced, and the description does not compensate fully for the missing parameter documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40% (2 of 5 parameters have descriptions). The description adds no additional meaning for the parameters beyond mark_text usage context. It does not explain limit, include_dead, nice_classes, or similarity_threshold, which are necessary for effective use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds trademarks whose whole mark sounds similar using Metaphone+trigram, and explicitly distinguishes from other tools like list_marks_containing_term and run_knockout_search. The verb 'find' and resource 'trademarks' are specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use and when-not-to-use guidance, including a detailed example (KWIK REWARDS not surfacing for QUICK) and clear warnings about thin results not supporting availability conclusions. It also recommends specific alternative tools (list_marks_containing_term, run_knockout_search).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions returning confidence scores and explanations, but lacks details on behavior such as whether the tool uses external data sources, deterministic output, or any limitations beyond the input schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that efficiently communicates the tool's function and output, with no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description provides the essential purpose but lacks details on number of recommendations, interpretation of confidence scores, or handling edge cases. It is adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters described. The description does not add meaning beyond the schema, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Recommend Nice trademark classes based on a business description.' It distinguishes from siblings like 'get_nice_classes' (which likely retrieves existing classes) by emphasizing recommendation and return of confidence scores and explanations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates input (business description) and output (relevant classes with scores/explanations), but does not explicitly state when to use this tool versus alternatives, nor when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses async behavior for authenticated users (1-2 minutes) and that it returns a processing handle. No annotations exist, so description carries the burden. Could clarify behavior for unauthenticated users, but overall clear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise two-sentence description with front-loaded purpose. The instruction about telling the user is relevant, though slightly verbose. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple one-parameter tool. Covers purpose, async behavior, return contents, and next steps. No gaps given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already describes serial_number with 100% coverage. The tool description adds no additional details beyond the schema, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool researches Office Actions for trademarks, listing specific return contents (refusal categories, OA/response context, cited marks, third-party registrations). This differentiates it from siblings like get_latest_office_action or draft_oa_response.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: before draft_oa_response for preliminary research. Provides async behavior and the follow-up tool get_office_action_research_status. Also instructs to inform the user it is running.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist. The description adds that resolving clients and portfolios requires authentication, but fails to disclose other behavioral traits such as whether the operation is read-only, what happens if no match is found, or any rate limits. Lacks comprehensive behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: the first states the purpose and lists all entity types, the second adds authentication requirement. No wasted words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 3 parameters and no output schema or annotations. The description covers basic purpose and auth, but lacks details on output format, confidence scoring, or what 'best match' entails. Adequate but incomplete for an agent to fully understand behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description rephrases entity types and subject_name from the schema without adding significant new meaning. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool resolves various trademark entities (owner, law firm, etc.) to the best match. It is specific about the verb and resources, but does not differentiate from sibling tools like search_trademarks or search_by_owner, which could also find entities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as search_trademarks or search_by_owner. The only usage note is about authentication for clients and portfolios, but no explicit when/when-not conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behaviors: it includes web research, market overlap analysis, and factor-by-factor scoring. However, it does not mention potential time/cost implications or any side effects. Given no annotations, the description provides adequate but not exhaustive transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the purpose, and includes essential details and a sibling comparison without any verbose or redundant phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Considering the complexity (13-factor analysis with web research) and the absence of an output schema, the description gives a good overview. It mentions key activities but does not specify output format or confirm if it's synchronous/asynchronous. Still, it provides enough context for the agent to understand what the tool does.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for serial_a and serial_b as USPTO serial numbers. The description adds context that these are for two marks and that the analysis compares them, but does not go beyond what the schema already conveys.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states it runs a full 13-factor DuPont likelihood of confusion analysis, mentions specific components (web research, market overlap, factor scoring), and distinguishes it from the sibling compare_marks tool by noting it is more thorough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear guidance: use compare_marks for a quick check first, then use this tool for deeper analysis. It positions the tool as the most thorough option, implicitly telling when to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the search is pure USPTO, returns 4-tier risk groups, includes dead-mark samples, and takes under a minute. It explains scoring behavior with goods_description. However, it does not explicitly state if it is read-only or require authentication, though that is inferred for a search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is detailed but well-structured, front-loading the main purpose and then adding specifics. Every sentence adds value, though it could be slightly more concise without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately explains return format (4-tier risk groups with confusion scores and dead-mark sample). It covers purpose, limitations, parameter usage, performance estimate, and prerequisites, making it complete for a complex search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers all parameters (100% coverage). The description adds value beyond schema by explaining why goods_description is strongly recommended (drives goods-relatedness scoring), how owner_name adds portfolio context, and provides usage guidance for design_codes and nice_classes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it runs an examiner-style knockout search with scoring via a unified knockout engine, specifying it is a pure USPTO conflict search over 14M trademark records. It distinguishes itself from siblings by explicitly mentioning what it does not do (domain/brand availability) and suggesting alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: it tells when to use the tool (for trademark knockout searches), what not to use it for (domain/brand checks), and recommends check_brand_availability as an alternative. It also advises passing goods_description when known and warns the user about the up-to-minute wait time.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description describes the tool as 'constrained' and 'safe', implying read-only behavior. It explains the tool's role as a fallback and its limited scope, adding behavioral context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: first states core purpose, second clarifies its fallback role, third gives usage recommendation. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of 6 parameters, nested objects, and an output schema, the description provides adequate context about the tool's role and usage scope. It doesn't need to explain return values due to output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 83%, so the baseline is 3. The description does not elaborate on parameters beyond mentioning analysis types, which is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs constrained business-level analytics queries without exposing schema details, and lists specific analysis types and entities. It distinguishes from siblings by being the default fallback for aggregate business questions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly recommends preferring this tool before chaining other tools for aggregate questions, giving clear guidance on when to use. It doesn't explicitly state when not to use, but the positive guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description transparently states what data is returned (prosecution stats, TTAB counts, contact info). It does not mention side effects or limitations, but for a read-only search tool, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, 18 words, with front-loaded verb and resource. It efficiently communicates purpose and returns without superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, the description covers return values. However, it misses hints on leveraging results with sibling tools (e.g., using found attorney IDs in get_correspondent_marks). This would enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no new meaning beyond the schema's parameter descriptions (e.g., not elaborating on search term format or limit behavior).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for trademark attorneys or law firms and lists specific returns: prosecution statistics, TTAB proceeding counts, and contact information. This distinguishes it from sibling tools like search_trademarks or search_by_owner.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like get_correspondent_marks or get_firm_deadlines. The description implies a general search use case but lacks when-not-to-use or follow-up suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the return format (portfolio statistics) but does not disclose whether the operation is read-only, pagination behavior, or any side effects. Given the lack of annotations, more detail would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose, followed by usage boundaries and return information. No unnecessary words; every sentence provides value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool with 2 parameters and an output schema, the description covers purpose, usage boundaries, and return structure. It does not mention matching behavior (e.g., exact vs. fuzzy), but the schema and output schema compensate sufficiently. The presence of many similar sibling tools is addressed by the clear usage boundaries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description adds no additional meaning to the parameters beyond what is already in the schema. The description does not elaborate on the owner_name or limit parameters further.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches for trademark owners by name and returns portfolio statistics. It explicitly distinguishes what it is not for (owner counts, rankings, etc.), making it easy to differentiate from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use ('resolve or list candidate owners') and when-not-to-use ('not for owner counts, rankings...') guidance. It does not name specific alternative tools, but the context is clear enough for an agent to infer alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.