mentalka-tests

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

No annotations are provided, so the description carries full disclosure duty. The verb 'List' plus zero parameters implies a safe read, but it says nothing about authentication requirements, result ordering, pagination, or whether the catalogue is filtered by user/account — all relevant for a listing endpoint.

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 action and resource, with zero filler. Nothing in it is redundant or padded.

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 listing tool with no output schema, the definition is minimally viable. It is missing the two things an agent would most want: what the response contains (e.g. test identifiers usable with start_test) and whether authentication or a locale scoping applies.

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 no parameters, so the baseline of 4 applies. There is no parameter syntax or formatting that the description could usefully add.

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?

Clear specific verb+resource: 'List the psychological screening tests' names exactly what is returned and where it comes from (mentalka.app). It is readily distinguishable from start_test and score_test, which act on a single test rather than enumerating them, though it never says so explicitly.

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 when-to-use guidance and no mention of alternatives. The agent must infer that this is the discovery step preceding start_test/score_test; nothing in the description confirms that relationship or rules out other contexts.

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 and does well: it discloses the consent gate, the no-fabrication rule for e-mail, and that the score is optional. It does not describe what happens on success/failure or any rate/confirmation behavior, leaving a modest gap for a tool that transmits personal data.

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?

Four short sentences, purpose front-loaded, then constraints in priority order (consent, no guessing e-mail, tone). Every clause earns its place with no repetition.

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 no-annotation, no-output-schema tool with 4 params, the description supplies the critical behavioral context (consent, e-mail provenance, optional score). It is complete enough to call safely, though it omits any note about the result of the request.

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 four parameters (test enum, email, score, consent) are already documented in the schema. The description reinforces the consent and non-inference constraints but adds no syntax or format detail beyond the schema; 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 and resource ('Send a request for a free consultation with the site's psychologist'), and the surrounding siblings (list_tests, score_test, start_test) are all test-management tools that this clearly is not. An agent can distinguish it immediately.

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 preconditions: call ONLY after the user explicitly asked, typed their own e-mail, and agreed to share it. It also states a negative ('Never invent or infer an e-mail') and soft guidance ('Offer it, do not push it'), leaving nothing 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?

With no annotations present, the description carries the full burden and it does disclose non-obvious behavior: the result may include helplines, and the output is a screening that should be framed carefully to the user. It does not describe validation/failure behavior when answer counts are wrong, which is a notable gap for a scoring 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?

Front-loads the core action in the first sentence, then packs parameter format and output-handling guidance into the rest with no filler. Slightly dense but each 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?

No output schema exists, so the description usefully hints that results may contain helplines and must be presented as screening only. Combined with the answers-format detail, this is complete enough to call and handle the tool correctly, though return structure and error handling remain undocumented.

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 67% (test and locale are documented), and the description adds real value beyond the schema by specifying the exact answer format per test: nine values 0-3 for PHQ-9 and 33 values 1-6 for SAS. That length/range detail is what the schema's generic integer array lacks.

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?

Specific verb + resource ('Score a finished test') that clearly separates this from sibling start_test (which begins a test) and list_tests. An agent can distinguish it without opening the 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?

The phrase 'a finished test' implies the prerequisite that a test must already be completed and answers collected, which routes the agent away from start_test. It also gives presentation guidance (helplines, screening-not-diagnosis disclaimer), but does not name an explicit alternative or state what to do if answers are incomplete.

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

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

With no annotations, the description carries the full burden, and it discloses a non-obvious behavioral contract: the tool returns questions but the agent itself must conduct the interview, feedback answers, and defer scoring to score_test. The prohibition on inventing answers is valuable behavioral disclosure. It does not cover side effects, idempotency, or return structure, keeping it 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?

Three short sentences, front-loaded with the tool's output, then the workflow, then the constraint. Every sentence carries distinct information with no repetition 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?

No output schema exists, so the description must convey what comes back; it does ('the questions and answer scale of a test'). It also maps the full pipeline to score_test. Minor gaps remain around the expected shape of collected answers, but nothing essential for correct invocation 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?

Schema description coverage is 100% – both enum parameters (test, locale) are fully documented in the schema, including test length and locale defaults. The description adds no parameter-level detail beyond the schema, so the baseline of 3 applies.

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

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

States a concrete verb+resource: retrieve the questions and answer scale for a test. The name 'start_test' is ambiguous on its own, but the description disambiguates it (it fetches test content rather than executing anything). It names score_test as the follow-up step, though it never distinguishes itself from list_tests.

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 usage flow: ask questions one by one or in small groups, collect answer values, then call score_test. It also adds a clear directive ('Do not guess or invent answers for the user'), which is real guidance. It lacks an explicit when-not-to-use or a contrast with list_tests, so it falls short of a 5.

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