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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered; the description adds valuable behavioral detail beyond that: cache 10 min (results may be stale), traversal bounded by max_paginas, and data-transforming behavior — outlier discarding via 1.5×IQR Tukey and calculation of quartiles/standard deviation. This tells the agent the tool does not merely return raw prices but transforms them. No contradiction with 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?

Four dense, purposeful sentences: purpose+methodology, composition, statistical calculations, and output+caching. No filler; the IQR detail and cache note each carry decision-relevant information an agent needs before invoking. The most important scoping fact (aggregation for ETP under IN 65/2021) 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 moderately complex aggregation tool, nothing essential is missing: purpose, underlying data sources, statistical behavior, output shape (detailed list + statistical summary + recommended sample without outliers), caching, and parameter semantics (covered by the 100%-coverage schema). An output schema exists so return values needn't be spelled out further.

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 schema itself is rich (max_paginas explains 'Cada página tem 500 registros', periodo_meses cites IN SEGES/ME 65/2021 art. 5, tipo maps to CATMAT/CATSER). The description adds only a light tie-in by referencing max_paginas in the composition flow. With the schema already doing the heavy lifting, 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?

The description names a specific verb+resource: 'Agrega preços praticados aplicando metodologia IN SEGES/ME 65/2021' — aggregating practiced prices under a named legal methodology. It further differentiates from sibling raw-search tools by explicitly naming its components (`compras_pesquisar_preco_material` or `_servico`) and describing the statistical aggregation output, making clear it is the analysis layer on top of those primitives.

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 use context: it composes the raw price-search siblings into an aggregate, and states the output is 'pronta para colagem em ETP' (ready for ETP documents), signaling when an agent should choose aggregation over raw search. However, it never explicitly states when NOT to use it or names a competing aggregate sibling (e.g., compras_aggregate_contratacoes_por_periodo) as an alternative, leaving some selection inference to the agent.

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