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

Annotations already declare readOnlyHint and idempotentHint, covering side-effect safety. The description adds format-specific behavioral details—such as 'original PDF binary for inline rendering' and 'self-contained interactive HTML with theme switching'—which go beyond the structured data. It does not discuss rate limits or errors, but these are less critical for a read-only retrieval 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 front-loaded with a concise summary, then gives the skill-preference guidance, then enumerates formats line-by-line. It is slightly redundant with the schema’s format descriptions but remains tight and scannable; no sentence is wasted.

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 compensates by specifying the return type for each format and noting the default. Annotations cover the safety profile. The only notable omission is any mention of payload size or pagination, but for a raw retrieval tool this is a minor gap, and the description is otherwise complete enough for correct 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%: both parameters are fully described in the input schema. The description largely restates the format parameter’s schema text and adds no additional meaning for the `enrich` parameter. Since the schema already does the heavy lifting, the description adds no extra value, which aligns with the baseline of 3.

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 opens with a specific verb ('retrieves'), a clear resource ('raw CV content'), and an explicit list of output formats. It distinguishes itself from siblings like get_cv_sections or get_cv_pdf_link by framing this as a low-level data-layer retrieval rather than a derived view or link.

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?

It explicitly tells the agent when NOT to call this tool: when the cv-analyst skill is available, prefer that skill, and it explains why (orchestration, formatting, artifact delivery, summarization). This is direct routing guidance with a named alternative and condition.

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 idempotentHint=true, so the agent knows this operation is safe and repeatable. The description adds that the result is a direct link to a PDF, which is slightly more specific than the tool name, but does not disclose any additional behavioral traits such as link expiry, need for authentication, or whether the link is dynamically generated. Given annotation coverage, the bar is lowercars, and the description is consistent but not enriching.

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, direct sentence that front-loads the key purpose without any filler. Every word contributes to understanding what the tool returns. Ideal conciseness for a zero-parameter read 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 there are no parameters, annotations cover safety, and an output schema exists to describe the return value, the description is fully adequate. Nothing else is needed for an agent to select and invoke this tool correctly; the only minor gap is usage vs siblings, but that is not required for completeness in such a simple 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 tool has zero parametersages, so the schema offers no parameter descriptions to cover. The baseline for no-parameter tools is 4 because nothing is needed in the description to clarify parameter usage. The description is appropriately free of parameter information.

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 is concise and specific: 'Return the direct link to the PDF version of the CV.' The verb 'return' and resource 'direct link to the PDF version of the CV' clearly identify the tool's function. This distinguishes it from sibling tools like get_cv, get_link, and get_google_scholar_link, as it targets a PDF-specific direct link.

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 provide any guidance on when to choose this tool over alternatives such as get_cv, get_link, or get_tailored_cv. There is no mention of use cases, exclusions, or relationships to sibling tools. While the name is fairly self-explanatory, the lack of explicit guidance makes this a gap.

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 and idempotentHint, covering safety. The description adds behavioral detail: returns sections separated by blank lines and reports unrecognized names with the list of available sections. This goes beyond annotations and helps the agent know what to expect.

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 short sentences that front-load the purpose and then detail behavior. No fluff or redundancy, making it easy to parse quickly.

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 covers the core behavior: input, output format, and error reporting. Combined with full schema coverage and an output schema, it's sufficient for an agent to call it correctly. It also hints at using list_cv_sections for available names via the schema parameter.

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 schema parameter descriptions are detailed (case-insensitive, '&' ignored, list_cv_sections reference). The main description doesn't add parameter details, but the schema already covers them, so 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?

Clearly states the verb 'Retrieve' and resource 'CV sections', and specifies it can fetch one or more sections in a single call. This distinguishes it from siblings like list_cv_sections (which lists names) and get_cv (which returns the entire CV), so an agent can tell them apart.

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 alternatives, nor does it mention exclusions. It implies usage for retrieving specific sections, but without guidance on when not to use it. The only hint is in the schema parameter description referencing list_cv_sections, which is not part of the main description.

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 idempotentHint=true, so the safety profile is covered. The description adds that it returns JSON representation, which is a small behavioral detail. It doesn't disclose error behavior (e.g., what happens if the ID doesn't exist) or any rate limits, but with annotations covering the main traits, a 3 is appropriate.

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?

One sentence, front-loaded with the verb and resource, and includes the return format. Zero waste. 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?

For a simple read-only retrieval tool with one parameter and an output schema present, the description is nearly complete. It doesn't explain error cases or ID format, but the output schema covers return values and annotations cover safety. The sibling context provides enough routing information.

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 0%, so the description must compensate. The description mentions 'stable ID' and 'entry_id' is the only parameter, which adds a bit of meaning (the ID is stable). However, it doesn't explain the format of the ID or how to obtain it, leaving some ambiguity. Baseline for 0% coverage would be lower, but the single parameter is self-explanatory from its name and the description's 'stable ID' phrase.

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 states a specific verb ('Retrieve') and resource ('a specific resume entry by its stable ID'), which clearly distinguishes it from sibling tools like list_entry_ids or query_by_topic. It doesn't explicitly name a sibling to differentiate from, but the resource and ID-based lookup are clear enough.

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: use this when you have a stable entry ID and need the full JSON representation. It doesn't explicitly state when not to use it or mention alternatives, but the context of sibling tools (list_entry_ids for enumeration, query_by_topic for search) provides implicit guidance. No explicit exclusions or alternative routing.

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 idempotentHint=true, so safety is covered. The description adds the composition of the returned context but does not disclose costs, size limits, or any edge-case behavior; with annotations present, this is acceptable but not enriched.

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?

One sentence, front-loaded action, colon-delimited facet list, and no filler. Every word contributes to scope or output composition.

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 one-parameter read-only tool with an output schema and safety annotations, the description gives the agent enough to select and call it. It is only slightly weakened by the lack of explicit routing advice against sibling tools.

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 one parameter and schema_description_coverage at 0%, the description's phrase 'for an entry' helps map entry_id to the target entry, but it adds no format, provenance, or guidance for obtaining valid IDs. Minimal compensation for the missing 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?

States a specific verb ('Get'), a clear resource ('full semantic context for an entry'), and enumerates the returned facets: topics, relationships, summaries, impact. The 'full' qualifier and the facet list distinguish it from sibling get_relationships or get_entry, which handle subsets.

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 only implies usage through 'full semantic context' and its four components. It does not explicitly say when to prefer this over get_relationships, query_by_topic, or get_entry, nor does it mention any exclusions.

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 and idempotentHint, so the description does not need to cover safety. It adds the specific output resource ('Google Scholar profile link') but does not describe any further behavior such as return format, null handling, or access prerequisites.

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 with no filler. Every word contributes to identifying the tool's purpose.

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 zero-parameter, read-only getter with an output schema and safety annotations, the description is complete. Nothing else is needed for an agent to invoke it correctly.

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 tool has zero parameters and the schema description coverage is 100%, so the baseline of 4 is appropriate. There is no parameter information for the description to supplement.

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 and resource: 'Return the Google Scholar profile link.' This clearly identifies a distinct output and differentiates it from sibling tools like get_link and list_links.

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 usage context is implied by the tool name and description: call this when you need the Google Scholar profile link. However, it does not explicitly name alternatives or state when not to use it, leaving the distinction from other 'link' tools to inference.

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 establish read-only, idempotent, closed-world behavior. The description adds that the tool returns a profile or document link and selects by network name, which is useful but does not disclose error handling, missing-name behavior, or any edge cases. No contradiction with annotations.

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 with no filler. Every part contributes to the core meaning, making it easy for an agent to parse quickly.

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?

This is a simple one-parameter tool with strong annotations and an output schema, so the description doesn't need to explain return values or safety. It could be slightly more complete by naming relevant siblings, but nothing essential is missing for calling it correctly.

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%: the single 'name' parameter is described with concrete examples and a pointer to list_links. The tool description itself adds no extra parameter meaning, so the 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 a specific verb and resource: it returns a profile or document link based on a network name. It does not explicitly contrast itself with sibling tools like list_links or get_cv_pdf_link, but the core purpose is unambiguous.

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 parameter description provides a useful hint: 'Use list_links() to see all available.' This implies the discovery flow when the caller doesn't know valid names, but the tool description itself does not explicitly state when to use get_link versus the many sibling link-specific 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds that it retrieves cross-references and relationships, which clarifies scope, but it does not disclose any additional behavior such as error handling, empty results, or performance characteristics. With annotations in place, this is acceptable 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 a single, front-loaded sentence that is concise and free of filler. It states the action and target clearly without unnecessary detail. This is an appropriate length for a tool with a single parameter.

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?

While the tool has an output schema (not shown), the description does not clarify the semantics of 'cross-references and relationships'—what types exist, how they are organized, or any limitations. It is a simple tool with one parameter, but the description leaves the agent guessing about the nature of the returned data. Given the existence of an output schema, the description could be more complete about the tool's 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 0%—the entry_id property has no description in the schema. The tool description does not compensate; it only mentions 'for a resume entry,' which adds little beyond the parameter name. The agent receives no guidance on the expected format, example values, or constraints for entry_id, making this a significant gap given the low schema coverage.

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 'Get' with a clear resource: 'cross-references and relationships for a resume entry.' This distinguishes it from sibling tools like get_entry (which likely returns the entry itself) and get_entry_context (which may return broader context). The phrasing is unambiguous and tells the agent exactly what data to expect.

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 no guidance on when to use this tool versus alternatives like get_entry_context or get_entry. There are no explicit when-to-use or when-not-to-use instructions, nor any mention of alternatives. The agent must infer its usage from the resource 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so safety is covered. The description adds the 'across the career' scope, but does not disclose any other behavioral traits like response size, pagination, or data granularity. It does not contradict the annotations.

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 states the purpose and the optional filter. Every word 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 simple one-parameter interface, the presence of an output schema, and read-only annotations, the description covers the essentials. It could mention what 'across the career' implies (e.g., time-based aggregation) but the current level is adequate 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?

Schema description coverage is 0%, so the description must compensate. It explains that the 'topic' parameter optionally filters results, which adds meaning beyond the raw schema. However, it does not specify allowed values, format, or edge cases, leaving some ambiguity for a single 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 tool retrieves skill proficiency levels, specifies the scope (across the career), and notes an optional topic filter. It is specific and distinguishable from sibling tools like get_cv or summarize_cv.

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 no guidance on when to use this tool versus alternatives such as query_by_topic or get_cv. It mentions optional topic filtering but does not explain when that filter is appropriate or how this tool relates to others.

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 convey read-only and idempotent behavior. The description adds valuable behavioral detail beyond that: the config controls section ordering, entry emphasis with omit semantics, profile override, and page budget, and the tool returns source code rather than a compiled artifact.

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, all load-bearing and free of repetition. The primary action, format options, config behavior, return type, and usage context are covered without a wasted word.

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 is a two-parameter generation tool with an output schema, annotations, and a focused description. It identifies the required parameter schema, format choices, key config semantics, and intended workflow; the only minor gap is that the full TailoringSpec schema must be resolved externally from the reference in the parameter description.

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, but the description adds meaning: it explains what tailoring_config controls (section ordering, emphasis, profile override) and the parameter description contributes weight semantics (0-2, 0=omit) and page budget. This exceeds the schema 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 opens with a specific verb and resource: 'Render a tailored CV from a TailoringSpec in LaTeX or Typst format.' It clearly distinguishes this from sibling tools like get_cv and summarize_cv by naming the specialized output (compilable source code) and tailoring behavior.

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 closing sentence gives explicit usage context: 'Use this tool after analyzing a job description to produce a targeted CV.' It does not enumerate when not to use alternatives, so it stops short of a 5, but the placement guidance is unambiguous.

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 idempotentHint=true, establishing the read-only safety profile. The description adds that line counts are 'approximate,' which signals imprecision, and 'available' signals that the list reflects actual sections present. This adds some behavioral nuance beyond annotations, though it does not cover details like ordering or grouping, which the output schema may address.

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 sentences, front-loaded with the core function in the first sentence and the rationale in the second. No word is wasted, and both sentences contribute distinct, valuable 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 (no parameters), the presence of an output schema, and annotations covering read-only/idempotent behavior, the description is nearly complete. It explains what the tool returns, why to use it, and the approximate nature of line counts; however, it does not clarify the relationship to the similarly named sibling 'get_cv_sections,' leaving a small contextual gap.

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 tool has zero parameters, so there are no parameter semantics to document. The schema description coverage is 100% vacuously, and the description does not need to compensate; the baseline for 0 params is 4.

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 the specific verb 'List' with a clear resource: 'available CV section names' and adds 'approximate line counts' to define the output. It clearly states the tool's function, but it does not explicitly differentiate itself from the similar sibling 'get_cv_sections,' so it stops short of 5.

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 second sentence, 'Helps AI assistants pick the right section for targeted queries,' gives a clear use case for the tool. It explains why an agent would call it, but it does not list any alternatives or when not to use it, which keeps it at a 4.

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 disclose that the tool is read-only and idempotent, so the description does not need to repeat those. It adds that the result includes labels and that filtering by section is optional, but it does not explain ordering, pagination, or how the empty default section behaves beyond the implied 'no filter' meaning.

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 entire description is one tight sentence that front-loads the core action and then adds the optional filter with all allowed values. There is no redundant phrasing or filler, and 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?

This is a simple list tool with one optional parameter and an output schema already present, so the description does not need to explain return structures further. It covers the key behaviors: listing all entry IDs, including labels, and optionally restricting by section type. That is sufficient for an agent to invoke it correctly.

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 input schema for 'section' has no description and no enums, so the description carries the full burden of parameter semantics. It explicitly lists the valid section values and explains that the parameter filters the results, which adds meaning well beyond the bare 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 a specific verb ('List') and resource ('all entry IDs with labels'), and it enumerates the filterable section types. It does not explicitly distinguish itself from sibling tools like get_entry or list_cv_sections, but the resource and filtering scope make the core purpose clear.

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 says the list can be optionally filtered by section type, but it provides no guidance on when to choose this tool over related tools such as get_entry, query_by_topic, or get_entry_context. No exclusions or alternative routing are given, so an agent must infer the appropriate 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds limited behavioral context by scoping results to 'profile and document links' and indicating completeness with 'all available', but it does not explain output format, ordering, or whether any links may be omitted.

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, focused sentence with no filler. It states the action and the target resource concisely, which is entirely appropriate for a zero-parameter tool.

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 low complexity, zero parameters, and presence of an output schema, the description covers the essential purpose. Minor gaps exist around link categories and how results are returned, but these are partially addressed by the output schema and the tool's simple nature.

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 tool has zero parameters, so no parameter semantics are needed. The schema fully documents the empty parameter set, and the description does not need to add anything beyond confirming the tool takes no input.

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 ('List') and resource ('profile and document links'), making the tool's purpose clear. It does not explicitly distinguish itself from sibling tools like get_link, get_cv_pdf_link, or get_google_scholar_link, but the 'all' vs specific-link distinction is implicit.

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 this is the tool for retrieving a complete set of links rather than a single link, but it does not explicitly state when to choose this over sibling tools such as get_link or get_cv_pdf_link. Usage context is understandable but left to inference.

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 disclose readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds a small behavioral detail by stating that the tool returns entry IDs with labels, but it does not discuss pagination, ordering, or 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 short sentences, front-loaded with the purpose and followed by the output summary. Every word earns its place, with no filler or repetition of schema 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?

The tool is simple and an output schema exists, so return values do not need description. However, with zero schema coverage on parameters and no mention of include_subtopics, the description is not fully complete for an agent deciding how to set that flag.

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 0% schema description coverage, the description must compensate for parameter meaning. It clarifies that the search is over resume entries with a topic, which partially covers 'topic', but it says nothing about 'include_subtopics' or how the default true affects results.

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 states a specific action and resource: 'Find resume entries annotated with a topic' and notes the output shape ('Returns entry IDs with labels'). This is clear and distinct from generic tools, though it does not explicitly compare against siblings like query_work or get_skill_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 gives no direct guidance on when to prefer this tool over alternatives such as query_work or get_entry_context. Usage is only implied by the phrase 'annotated with a topic', and no exclusions or alternative conditions are 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description doesn't need to restate safety. It adds the markdown output format and the three filter dimensions, which is useful. However, it omits behavior when no filters are provided (e.g., returns all or empty), filter combination logic (AND vs OR), and date range inclusivity—details that would aid correct invocation.

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 states the core action and output format with no fillers. Every word earns its place, making it optimally concise.

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 5 optional parameters and an output schema (which likely documents return structure), the description covers the main filtering dimensions and markdown output. Yet it lacks guidance on default behavior, filter combination semantics, and the role of the 'enrich' parameter in practice. For a filtered retrieval tool of this complexity, more context 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 only 20% (only 'enrich' has a description), so the description must compensate. It names the filter types (company, date range, topic) which maps to company, start_year/end_year, and topic parameters, adding meaning beyond the bare schema. However, it doesn't clarify parameter format (e.g., year strings) or how enrich relates to the filter criteria, leaving gaps.

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 filters work entries by company, date range, or topic, and returns markdown. The verb+resource+criteria are specific, making the purpose unambiguous. However, it doesn't explicitly distinguish itself from the sibling query_by_topic, which likely narrows the scope; this is a minor gap.

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. It doesn't mention that query_by_topic exists for topic-only queries, nor does it state any prerequisites or scenarios where this is preferred. The agent must infer usage from the schema 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?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds the fallback context but discloses little about the tool's internal behavior, such as how the CV is selected or how include_citations affects processing.

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 short sentences deliver the core purpose and usage guidance with zero filler. The key fallback message is front-loadedaine; the alternative routing appears immediately after.

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 covers the main decision an agent needs to make: whether to use this tool or the skill. An output schema existsched seasons it doesn't need to explain return values, and 100% schema coverage handles parameters. The main gap is that it never specifies which CV is being summarized, but the fallback framing and routing guidance make the tool usable.

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 every parameter has a description with defaults and examples slash variants. The description adds no parameter-specific detail, but with complete schema documentation the 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 opens with 'Fallback CV summarization' — a specific verb, resource, and clear role. It distinguishes the tool from the cv-analyst skill and indicates why it exists, making its purpose unmistakable.

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?

It explicitly states when to use the tool ('clients without Agent Skills support') and when not to ('prefer invoking that skill instead'), and names the alternative with concrete reasons. This is a model example of routing guidance.

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