Dr. Mais Vida

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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description adds real behavioral value: every statement must carry a citation and source, and when no reliable source exists the tool explicitly says it found nothing. It also discloses that it will refuse diagnostic and prescription requests, which is useful abstention behavior not visible in the schema or 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?

Three short sentences, zero filler: grounding source first, citation requirement and refusal path second, scope exclusions last. The most decision-relevant constraint (official base only, cited) is front-loaded.

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 one-parameter, read-only tool with no output schema, the description covers grounding, citation behavior, fallback when no source is found, and scope limits. Only the shape/length of the returned answer is left unspecified, a minor 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?

Schema coverage is 100% and the single 'question' parameter already documents Portuguese language and the 400-character limit. The description adds only that the question should be a general health or exam doubt, which is context rather than syntax, 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 and resource: answers a general health or exam question, grounded solely in the official guidelines of the Dr. Mais Vida base, with a citation per statement. The clause 'não usa dados da pessoa' implicitly separates it from check_lab_result (personal lab data), though no sibling is named 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?

Gives clear exclusions: no personal data, no diagnosis, no medicine or dosage recommendation, and only general doubts. These boundaries steer the agent away from personal-result tools, but it never names an alternative sibling to use instead for those cases.

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 openWorldHint=false, so safety is covered; the description adds real value by disclosing the required input provenance (the report's own range, not a default) and the scope limit that it does not interpret or diagnose. It also sketches the shape of the answer (inside/below/above plus a pointer). Beyond that it says nothing about missing-range behavior or precision/rounding.

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, front-loaded with the outcome, then the input constraint, then the scope limit. No filler; every sentence carries information an agent needs.

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 and full parameter coverage, the description covers purpose, required inputs, and the diagnostic-scope boundary. The remaining gap is what happens when neither range_low nor range_high is supplied, since those are optional.

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 genuinely adds semantics the schema lacks: range_low/range_high must be taken from the person's printed report because reference ranges are lab-specific. That is a meaningful constraint on how to populate two optional parameters.

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 compares an exam value against the reference range printed on the person's report and returns inside/below/above, plus a pointer to where to understand the result. It implicitly separates itself from ask_health_guidelines by saying 'Não interpreta nem diagnostica', though it never names a sibling 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?

Gives clear operational guidance — pass the range from the report itself via range_low/range_high, because ranges vary by laboratory and a generic range is not used. It also sets a boundary ('não interpreta nem diagnostica'), which tells the agent when to hand off. It does not name the alternative tools or state exclusions by name.

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 cover readOnlyHint and openWorldHint, so the bar is lower; the description still adds real value by disclosing the result cap ('até 5 artigos') and the returned fields (título, endereço, resumo). No mention of ranking/relevance behavior, but the key behavioral trait (a bounded top-5 list) is disclosed.

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, front-loaded with the verb and scope, then output shape, then usage examples. The parenthetical topic list is slightly long but serves the disambiguation purpose, so it earns its space.

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 result count and fields. For a single-parameter read-only search, nothing an agent needs to call it correctly 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 coverage is 100%, so the baseline is 3; the description goes beyond it by giving concrete example values ('ferritina baixa', 'TSH alto') that clarify the expected free-text granularity and language. It does not add syntax constraints, but none are needed for a single string.

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 ('Procura') and resource (blog articles from Dr. Mais Vida), enumerating the covered exam topics. It's clearly distinct from check_lab_result and ask_health_guidelines in substance, but it never names the siblings to make the boundary explicit.

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?

Explicitly instructs 'Use com o nome do exame ou a dúvida' and supplies two concrete example queries, giving clear context for invocation. It stops short of stating when NOT to use it or which sibling to prefer for guidelines vs. lab-result interpretation.

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