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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description additionally discloses important runtime behavior: count mode reads only totalRegistros, value modes scan pages, the 25-page/12,500-record cap, truncado=true signaling, internal concurrency of 4 calls, and a 30-minute cache. This is excellent transparency beyond the 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?

The description is compact and well-structured with bolded mode headings. Every sentence carries useful information: mode semantics, performance characteristics, limits, truncation behavior, concurrency, and cache. There is no filler or repetition of schema content.

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?

The output schema and annotations already cover return values and safety semantics, so the description only needs to cover behavior and limits, which it does thoroughly. The main gap is the lack of explicit routing guidance against similar aggregation/indicator siblings, but this is minor for a tool with this much structured support.

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 the schema already documents each parameter, establishing a baseline of 3. The description adds value by explaining what the 'metrica' modes actually do mechanically and by documenting the truncation ceiling and page-scan behavior, which is not fully captured in the schema.

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 opening line clearly states the tool produces a time series of PNCP contracting data grouped into buckets, which is a specific verb+resource pairing. It is clearly an aggregation tool and distinct from the many single-record/list lookup siblings, 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?

The description gives strong within-tool guidance: use 'count' for trends, only enable value modes when necessary, and notes that the 'esfera' filter only matters in value mode. It does not explicitly compare against siblings like compras_comparar_periodos_contratacoes, but the context is clear enough for an agent to decide when this aggregation is appropriate.

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