GMCA Certainty Matrix Validate

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

No annotations are provided, so the description carries the full burden, and it does disclose meaningful behavioral traits: the explanation is 'kort, neutraal' and must not be used to suggest or fill in an answer. It does not state permissions, reversibility, or response shape, but for an explainer operation the safety-relevant behavior is well covered.

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

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

Two sentences, front-loaded with the core action and followed by the usage constraint. No redundant restatement of the name or title, and every clause carries information.

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

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

For a single-parameter, read-only explainer the description is complete: it states what is produced (a short neutral explanation plus a concrete example), the trigger condition, and the forbidden use. No output schema is needed because the return content is described inline.

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

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

Schema description coverage is 100%, and the single parameter's schema text already names the source of the id ('uit get_validate_questions, bv. psf-1a'). The description adds no further parameter detail, which is acceptable given the schema does the work, so the baseline 3 applies.

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

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

States a specific verb (geeft een toelichting en een concreet voorbeeld) applied to a specific resource (één specifieke Validate-vraag). This clearly separates it from get_validate_questions (retrieve) and submit_validate_answers (answer), so an agent can route correctly without opening any 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?

Explicit when-to-use ('ENKEL wanneer de gebruiker zelf aangeeft de vraag niet te begrijpen of twijfelt over de betekenis') and when-not ('nooit standaard, en nooit om zelf een antwoord te suggereren of in te vullen'). Both the trigger condition and the prohibited use are spelled out.

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

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

No annotations are provided, so the description carries the full burden. It discloses the return contents (11 questions, each with explanation and example) and the critical usage constraint that answers must not be inferred. It does not discuss permissions or side effects, but 'Geeft ... terug' makes the read-only getter behavior evident.

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 purpose is front-loaded in the first clause, followed by the essential usage constraints. The capitalized emphasis is longer than ideal but every sentence carries operational weight (individually, literally, no self-fill, no steering).

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 must carry the return information, and it does: item count and per-item structure (neutral explanation + example). For a simple zero-param getter with no annotations, this is essentially complete; only sibling routing is 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline of 4 applies; the description correctly implies a parameterless fetch.

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 and resource: it returns the 11 official GMCA Certainty Matrix Validate questions, each with a neutral explanation and example. The scope and content are unambiguous, though it never explicitly distinguishes itself from the sibling explain_validate_question or submit_validate_answers.

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 strong behavioral directives: ask each question individually and literally, collect Ja/Deels/Nee per question, never self-fill from a project description, and only share the explanation when the user doubts without steering the answer. It lacks explicit routing versus the siblings (e.g., 'call before submit_validate_answers'), which keeps it at 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?

With no annotations this description carries the full burden and does substantial work: it discloses that output is qualitative with no scores or status labels, that consent gates data storage into the GMCA dataset, that nothing may be stored silently, and that no company/project names may be collected. It does not cover what happens if consent=false, whether answers are still processed, or error behavior, so it stops short of a 5.

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?

Purpose is front-loaded in the first clause, followed by the consent precondition and the optional-fields guidance. Three dense sentences with no filler, though the Rules v1.1 citation is somewhat extraneous detail an agent does not need in order to invoke the 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?

For a 7-parameter tool with a nested answers object, no output schema and no annotations, the description covers the call preconditions, privacy constraints and the qualitative nature of the result. It does not describe the shape or content of the returned result beyond 'no scores/status labels', leaving some gap for a tool whose output schema is absent.

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

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

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the semantics of consent (must be asked explicitly beforehand), of answers (all 11 question IDs from get_validate_questions), and of the optional context fields as coarse buckets never containing names, including why they are wanted.

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+resource: it processes the user's Ja/Deels/Nee answers to all 11 questions from get_validate_questions and returns the qualitative result. It explicitly names the sibling get_validate_questions as the source of the answers and rules out the misleading interpretation that it produces scores or status labels.

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

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

Explicit ordering and precondition: ask the user for consent BEFORE calling, never store data silently. It also tells the agent which additional fields to collect (sector/companySize/projectType/investmentRange) and that these are optional if the user declines, so the agent knows both what is required and what may be skipped.

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