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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false), and the description goes well beyond them: per-call limits, the pagination continuation contract via has_more, and the non-obvious failure mode that omitting pecaId silently mixes documents and yields wrong excerpts.

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-loaded with what it does, then usage, then the pagination rule, then the critical warning. No filler; every sentence (limits, continuation, pecaId warning) 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, but the description explains the return contract (has_more / proximaPagina) and the key input pitfall. Combined with annotations covering safety, an agent has everything needed to call it correctly.

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 baseline is 3. The description adds real meaning by clarifying that pecaId is effectively mandatory despite the schema labeling it 'opcional', and by binding inicio to proximaPagina for continuation. It adds value over the structured fields without fully documenting inicio/fim beyond 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?

States a specific verb+resource ('Lê o texto de uma ou mais páginas') with concrete scope limits (max 8 pages / 40k chars). Its role is distinguished from listar_pecas and buscar_autos, which it names as the sources of pecaId, so an agent can place it correctly among siblings.

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 says when to use it ('Use após uma busca para ler o conteúdo completo de uma evidência') and gives the continuation rule (on has_more, call again with inicio = proximaPagina; do not recompute). The pecaId prerequisite is stated as a hard requirement.

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