Merron

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false. The description adds a minor behavioral note about not classifying unanswered questions, but it does not disclose other behavioral traits such as whether results vary by product state, rate limits, or caching behavior. Given rich annotations, this is a weak addition.

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 short sentences packed with relevant constraints and no filler. The structure is front-loaded with purpose followed by usage rules, though it could be slightly tighter.

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, and the description does not explain the return format or structure of the questions/explanations. For a tool with a complex nested parameter and no output schema, omitting return-value details and deeper parameter semantics leaves significant gaps 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 description coverage is 0% for the sole 'facts' parameter, which is a complex object with additionalProperties accepting boolean, the enum ['provider','deployer','both'], or null. The description only says 'Pass only known user answers; omit unknown values or use null,' which is helpful but fails to explain the expected keys or the provider/deployer/both enum semantics, leaving critical ambiguity.

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) and resource (AI Act screening questions and explanations) scoped to a selected AI product. It is clear what the tool returns, though it doesn't explicitly differentiate itself from siblings like merron_screen_ai_act, which likely also deals with AI Act screening.

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 some invocation guidance: 'Pass only known user answers; omit unknown values or use null' and clarifies that it 'Does not classify or assume unanswered questions mean No.' However, it does not state when to use this tool versus siblings such as merron_scan_project or merron_screen_ai_act, leaving the selection context 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?

Annotations already declare readOnly, idempotent, closed-world and non-destructive, but the description adds substantial behavior beyond them: a mandatory consent gate before data leaves the user's environment, and explicit non-capabilities (no URL fetching, no code execution, no input persistence, no access to private cases). This is exactly the extra context annotations cannot convey.

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 front-loaded: purpose and return shape first, then the consent prerequisite, then the prohibitions. Dense and largely waste-free, though the guardrail sentence packs four distinct exclusions into a single long clause, slightly reducing scannability.

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 carries the return contract and does so ('file/line references and follow-up questions'). Safety semantics, consent flow and scope limits are all covered; the only omission is any hint about the 12-file / 8,000-character input caps, which the schema does enforce on its own.

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%: sharingConfirmed is documented in the schema, while the files array (path/text/startLine, max 12 items, 8000-char text) has no per-property description. The description reinforces the consent semantics of sharingConfirmed ('obtain the user's agreement', 'user-selected excerpts') but adds nothing about the files payload shape or limits, 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?

States a specific verb ('Find') and precise target artifacts (AI integrations, model calls, disclosure wording, sensitive-use wording) scoped to 'user-selected project excerpts.' The clause 'Returns file/line references and follow-up questions, not a legal classification' explicitly distinguishes it from the sibling merron_screen_ai_act, which is the classification tool.

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?

Gives an explicit precondition ('First explain that the excerpts will be sent to Merron and obtain the user's agreement') plus hard boundaries on what not to send (secrets, personal customer records, whole repositories, unauthorised files). It does not explicitly state when to prefer this over merron_screen_ai_act, so it falls short of the full when/when-not/alternatives bar.

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 only cover the safety profile (read-only, idempotent, closed-world, non-destructive). The description adds substantial behavioral context beyond that: it discloses what the tool does NOT do (no document checking, no AI model, no report saving, no account access, no certification) and enforces a strict epistemic rule that unknown answers stay unknown — highly valuable guardrails for an agent.

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?

Front-loaded with the core action, then outputs, then caveats, with no throwaway sentences. It is dense and slightly repetitive ('Never infer confirmation' / 'Unknown answers remain unknown'), but each sentence adds distinct 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?

With no output schema, the description correctly enumerates returns ('conditional screening result, unresolved routes, missing questions and official references'). Combined with the explicit scope limits, it is close to complete for a nested-object, 2-param tool, though the 'facts' object keys remain unspecified.

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 50%, with the meaning of the 'facts' object largely carried by the description. The text clarifies the confirmation requirement ('facts the user has explicitly confirmed') and the null-handling semantics ('Unknown answers remain unknown'), which maps to the null enum value. The provider/deployer/both enum values are not elaborated, keeping this short of a 5.

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: 'Run Merron's versioned, bounded AI Act rules on facts the user has explicitly confirmed.' It also distinguishes its scope from the scanning sibling by explicitly stating 'This computation does not check documents,' so an agent can separate it from merron_scan_project without opening a schema.

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?

Usage is implied rather than stated: the tool is for facts the user has already confirmed ('Never infer confirmation... from source code'). There is no explicit naming of alternatives (merron_get_questions, merron_scan_project) or a clear when-to-use/when-not statement, so routing among siblings must be inferred.

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