Patent PreCheck

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 disclosing behavior. It mentions the analysis outputs (statute hints, overlap theme, distinction checklist) but does not state whether the tool is read-only, requires authentication, has side effects, or how results are returned. It also doesn't mention that confirm_upload implies a user confirmation step. For a tool with no annotation coverage, this is a significant 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, with the core purpose in the first sentence and the usage condition in the second. No wasted words, and the most important information is front-loaded. Efficient and scannable.

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 comparison tool with four parameters and no output schema, the description covers the main inputs and the nature of the analysis. It lacks details on error handling (e.g., patent not found), the exact structure of the checklist, or whether a filename is required. Given the complexity, it is adequate but not rich; the absence of annotations and output schema means more could be said.

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 four parameters. The description adds no extra meaning beyond what the schema provides—it does not elaborate on the format of code, patent_id, or confirm_upload. Baseline 3 is appropriate since the schema does the heavy lifting, but the description doesn't enhance 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 states a specific verb (compare) and resource (invention text to a known US patent), and lists the analysis types (embedding similarity, prior-art risk). It also names the triggering condition ('when the user names a specific reference patent'), which differentiates it from siblings like precheck_search_corpus and precheck_lookup_patent. The purpose is unambiguous and distinct.

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 an explicit when-to-use condition ('Use when the user names a specific reference patent'), which clearly routes the agent away from search-based tools. It does not explicitly mention when not to use it or name alternatives, but the condition is enough to guide selection among the sibling tools. Slight gap: no mention of what to do if no patent is named.

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 does disclose 'Offline heuristic — informational only. No network call,' which is useful behavioral context implying low latency and non-authoritative results. However, it omits any detail about side effects, deterministic behavior, or whether it is read-only (though 'suggest' implies). It adds some value but could go further given zero annotation coverage.

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 with zero fluff. The primary purpose is front-loaded, and the behavioral caveat follows immediately. 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 suggestion tool with fully documented parameters and no output schema, the description is largely sufficient: it names the input, the purpose, and two key behavioral traits. The only gap is that it doesn't describe what the response looks like (e.g., a list of codes with confidence scores), which would help the agent know what to expect. Given the low complexity, this is a minor omission.

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 baseline is 3. The description adds only a general reference to 'invention description,' which maps to the 'code' parameter, but does not elaborate on 'limit' or 'invention_kind' beyond what the schema already provides. It does not compensate for any schema gaps because there are none.

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 the specific action 'Suggest' and the resource 'Cooperative Patent Classification (CPC) codes for an invention description,' which clearly distinguishes it from prior-art or legal-context tools. However, it does not name an alternative sibling or explicitly differentiate itself from the many other precheck_* tools, so it stops short of the highest tier.

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?

There is no guidance on when to use this tool versus alternatives like precheck_prior_art or precheck_rejection_patterns. The description never mentions conditions like 'if the user needs classification hints' or 'when exploring patent categories.' The agent must 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?

No annotations are provided, so the description carries the behavioral burden. It clearly indicates a retrieval operation ('Return download URLs') and an authorization prerequisite ('Requires report_id and session_key'), but it does not disclose whether the operation has side effects, whether URLs expire, or whether any special output handling is needed. This 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 a single front-loaded sentence that states the action, scope, return type, and required inputs without fluff. The parenthetical deliverable list adds useful specificity without bloat.

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 two-parameter retrieval tool with no output schema, the description covers the essential points: what it returns, for which resources, and what credentials are needed. It could be more explicit about error cases or URL expiry, but nothing required for correct selection and invocation is obviously missing.

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 interface schema already explains report_id (format) and session_key (header/stored key, not query string). The description merely repeats the required parameters without adding further semantic detail, so a 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 states a specific verb and resource: 'Return download URLs for finalized ICR deliverables', with a parenthetical list of deliverable types. This is clearly distinct from siblings like precheck_score or precheck_start_review, which focus on scoring or starting a review.

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 clear context: the tool is for finalized ICR deliverables, which implies it is not for in-progress work, and it names the required credentials (report_id and session_key). It does not explicitly name alternatives or exclusion conditions, but the purpose is specific enough that an agent can infer 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 of behavioral disclosure. It does add a meaningful caveat ('Informational only — not legal advice'), signaling the agent that this is non-authoritative. However, it does not disclose what happens with the uploaded code, whether this is a safe read-only operation, or what the 'snippet' entails, leaving behavioral gaps given the lack of annotation coverage.

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 with zero waste. The core purpose is front-loaded in the first sentence, and the caveat is a separate terse sentence. Every word earns its place; the jurisdictional detail (CAFC, USPTO, Alice/§101) is dense but directly useful.

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 no output schema and no annotations, the description states what it returns ('short snippet of guidance') and its informational status. But it does not specify the snippet's format, how the code input relates to retrieval, or how it fits into the PreCheck workflow alongside the other siblings. Given the complexity of the tool's legal context, more could be said without an output schema to rely on.

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% — code and confirm_upload are both documented in the schema itself. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies. The description's 'invention' phrasing loosely maps to the code parameter but adds no syntax or formatting detail.

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 ('Return a short snippet') and resource ('current US software-patent legal guidance'), further narrowed by jurisdiction and doctrine (CAFC, USPTO, Alice/§101). This clearly distinguishes it from the siblings, none of which provide legal guidance — compare_to_patent, prior_art, and rejection_patterns all serve different functions.

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 phrase 'relevant to scoring this invention' implies this fits into the scoring workflow, giving some contextual placement. However, no sibling is named and there is no when-to-use versus when-not-to-use guidance, which matters given 11 siblings. The guidance is implied rather than explicit.

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 transparency burden. It discloses the data source (USPTO), optional prior-art corpus join, and lack of auth requirements. It does not mention error handling or rate limits, but for a simple lookup this is sufficient.

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 pack all essential information: the operation, source, optional feature, return fields, and auth requirement. No redundancy or filler.

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 lists the return fields and mentions the optional join, which is adequate for a simple lookup tool. It does not cover error cases or pagination, but given the tool's straightforward nature, it is mostly 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% and descriptions already document both parameters. The description adds value with an example patent ID, clarifies the optional excerpt behavior, and explains the prior-art corpus join (a feature tied to the tool's behavior). This exceeds 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 clearly states the tool resolves a US patent/application number and returns specific fields like title, status, CPC, excerpt, and URL. This distinguishes it from sibling tools that perform comparisons, suggestions, or 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?

The description implies use when basic patent info is needed and notes no API key is required, but does not explicitly state when to prefer this tool over alternatives like precheck_search_corpus or precheck_prior_art. No when-not-to-use 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?

With no annotations present, the description carries the transparency burden. It explicitly says 'No network call,' signaling a local, read-only reference operation, and the verb 'List' reinforces that no mutation occurs. It does not detail output formatting, but this is minor for a zero-parameter reference 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?

Two tight, information-dense sentences. The first states exactly what the tool returns; the second gives the use case and a cost/behavior cue. 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 zero-parameter, no-output-schema reference tool, the description is complete: it identifies the returned content, the intended use, and the fact that no network call occurs. Nothing critical is missing for correct selection and 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?

The tool has zero parameters and 100% schema coverage, which is the baseline 4 case. No parameter explanation is needed because there are no parameters to clarify.

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 ('List'), a precise resource ('five scoring pillars with statutes and weights and the band rules'), and explicitly ties it to precheck_score for explaining scores. This clearly differentiates it from the scoring tool itself and other 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?

It gives a clear trigger condition: 'Use this to explain a score to the user.' It does not explicitly name alternative tools or exclusion criteria, but the reference-only role is evident from the phrasing and the 'No network call' note.

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 mentions the pipeline similarity to precheck_score but does not disclose whether the operation is read-only, has side effects, rate limits, or authentication requirements. It also does not describe any error conditions or edge cases. The description is thin on behavioral transparency for a tool with zero annotation coverage.

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 with no redundant words. It front-loads the purpose and immediately provides the key differentiator from precheck_score, followed by a direct instruction on how to pass input. 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?

Since there is no output schema, the description appropriately lists what will be returned (titles, sources, similarity scores, URLs), which is essential for the agent to know. It also mentions the pipeline and clarifies the focus. It does not elaborate on all parameters, but the schema covers those. The only minor gap is a lack of explicit usage conditions beyond the precheck_score contrast, but overall it is fairly complete for a retrieval-focused 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 100%, so the schema already documents all five parameters. The description adds the instruction 'Pass invention text via `code`', which reinforces the primary input but does not provide new semantic meaning beyond what the schema states (e.g., code is 'Source code or invention description'). This is baseline level for well-documented schemas.

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: returning the closest prior-art matches (titles, sources, similarity scores, URLs) for an invention. It also distinguishes itself from the sibling precheck_score by specifying it 'focuses on retrieval results', which helps an agent differentiate between the two.

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 usage hint by comparing itself to precheck_score ('Runs the same analyze pipeline as precheck_score but focuses on retrieval results'), indicating when this tool is more appropriate than that sibling. However, it does not explicitly mention when not to use it or discuss other sibling alternatives, so it lacks explicit exclusions but offers solid contextual 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?

No annotations are provided, so the description carries the behavioral disclosure burden. 'Preview' strongly implies a read-only, diagnostic operation, and the listed signals describe the kind of output the agent can expect. It does not, however, disclose upload/data-handling implications, tier effects, or how the preview relates to an actual filing, which limits 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 compact sentences, with the output preview front-loaded and the usage context in the second sentence. 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?

For an agent, the description plus fully-documented schema covers what the tool does, when to call it, and what kind of outputs to expect. It is slightly incomplete only because there is no output schema and no annotation coverage to explain side effects or return format in more detail.

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 code, tier, filename, and confirm_upload. The description adds no parameter-level detail; this is the baseline-3 case where the structured schema does the work.

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 ('Preview') and a concrete resource ('examination-risk signals'), then enumerates what those signals are: similar office-action rejections, abandonment patterns, and statutory basis. This makes the tool's role clear and distinguishable from patent-search or scoring siblings, though it does not directly contrast them.

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 to use this tool after precheck_score and states the goal: explain prosecution risk. There is no when-not-to-use or alternative branching, but the sequence guidance is a clear usage directive.

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 a key behavioral trait: the requirement for user confirmation ('get user yes') and the implication that nothing is uploaded without confirm_upload. It also implies analysis rather than modification by using 'run a pre-check.' However, it does not explicitly state read-only behavior, potential side effects, or any rate limits. The description is partially transparent 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 is information-dense and well-organized: it starts with the purpose, lists return values, and ends with usage instructions. It is somewhat long but each sentence contributes value—no filler. The structure is front-loaded with the core action and then provides necessary details, making it 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 absence of an output schema and annotations, the description does a good job of covering the essential return values (score, pillars, band, etc.) and the required confirmation workflow. It explains what the tool returns and how to invoke it correctly. While it doesn't interpret the score or band semantics, that's not necessary for invocation. The description is sufficiently complete for an agent to call this tool effectively.

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 all parameters are already documented. The description adds some operational context, such as 'pass the text inline via `code`' and the flow for confirm_upload, but these largely restate what the schema conveys. Since the schema does the heavy lifting, the description's contribution is marginal, aligning 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 clearly states the tool's function: 'Run a prior-art density / risk-profile pre-check on source code or an invention description.' It also enumerates specific return values (score across four pillars, filing-readiness signal, band, etc.), which distinguishes it from sibling tools like search or lookup. The description is not a tautology and provides concrete, scoped 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 description provides concrete usage steps: 'Show filename + size and get user yes, then pass confirm_upload: true. Pass the text inline via `code`.' These are clear operational instructions. However, it does not explicitly state when to use this tool versus alternatives like precheck_prior_art or precheck_pillars, nor does it mention exclusions. The guidance is helpful but lacks comparative 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, so the description carries the full burden of behavioral disclosure. While it mentions the search method and cost, it omits the critical requirement that confirm_upload must be set to true after user confirmation, which is a required parameter and a behavioral step. It also does not state whether the tool is read-only or if it uploads the provided code. This leaves a significant gap in what an agent needs to know before invoking.

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, zero fluff. The primary purpose and key differentiator (cost, no LLM scoring) are front-loaded, and every word contributes to the tool's selection and use.

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 the output (ranked matches with similarity scores) but omits the required confirmation step and does not clarify the role of the tier or limit parameters beyond what the schema says. Given there is no output schema, the description should at least mention the confirmation prerequisite, which it does not. Overall, it is adequate but incomplete for a tool with a required confirmation 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?

Schema description coverage is 100% for all five parameters, so the schema already documents them. The description does not add any parameter-specific details beyond what the schema provides, meeting the baseline of 3 but not exceeding it.

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 ('search') and resource ('2,200,000+ prior-art corpus'), and immediately distinguishes itself from the sibling precheck_score by noting it does not use LLM scoring and is cheaper. This clearly separates it from similar tools and tells an agent exactly what the tool does.

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 names the alternative (precheck_score) and gives the condition for choosing this tool: 'when you only need references.' This is a direct when-to-use statement with an alternative, satisfying the highest bar for usage 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 provided, the description must carry the full burden of behavioral disclosure. It only mentions the required credentials, but does not state whether the operation is read-only, what happens for invalid/expired sessions, or any error behavior. It also doesn't describe the response format. This is a significant gap for a tool with zero annotation coverage.

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 zero waste. The purpose is front-loaded, and the prerequisite is stated immediately. 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 two-parameter status check with no output schema, the description covers the core purpose and prerequisites. It could benefit from clarifying what 'status' includes or error handling, but given the tool's simplicity, it is reasonably 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 the parameters are fully documented in the schema. The tool description only repeats that they are required and come from the access email, which adds no new information. Baseline of 3 applies since the schema does the heavy lifting.

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: 'Return status for an active Interactive Code Review session.' It specifies the resource (session status) and the verb (return), and this is distinct from sibling tools which handle comparisons, scoring, searches, or starting reviews. No ambiguity.

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 you need session status, and it provides a prerequisite (requires report_id and session_key from the access email link). However, it does not explicitly contrast with alternatives or state when not to use it. The guidance is clear context without 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?

With no annotations, the description carries the behavioral burden. It clearly discloses that the tool returns a URL for the user to start a review, does not claim the tool itself charges the user, and notes the paid/promo-unlocked access model. This is sufficient transparency for a low-risk URL-returning operation, though it could mention whether invoking it creates any session or side effect.

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 with no filler. The primary behavior and commercial qualifier are front-loaded, and the usage context is delivered concisely in the second sentence.

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 URL-returning tool, the description gives the agent the purpose, the workflow context, and the return value type. There is no output schema, but the description sufficiently explains what the tool produces. It does not specify the URL format or what happens after the user opens the URL, but those are not essential 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?

The schema description coverage is 100%, so the parameters (email, promo, report_id) are already documented in the input schema. The description adds no additional parameter-level meaning, which is acceptable because the schema already carries the semantic load.

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 ('Return the URL') and resource ('paid Interactive Code Review') and distinguishes the tool from siblings by describing what the review does: strengthen pillars with evidence and produce a filing package. It also anchors the tool in the workflow with 'Use after precheck_score', making its role clear among the sibling 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 explicitly says to use this tool 'after precheck_score when the user wants to act on the result', giving a clear trigger and prerequisite. It does not enumerate alternatives or exclusion cases, but the workflow context is clear enough for an agent to know when this tool is relevant.

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