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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. Beyond that, the description adds genuinely useful context: this call is credential-gated, can fail without the right code, and free examples bypass the paywall. What it omits is what happens on an auth failure or how large the returned Markdown can be.

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?

It is short, but the structure is poor: the opening sentence is a run-on that buries the purpose under authorization clauses, and the trailing "The examples are free." is cryptic and unattached to any concrete action. Two sentences, yet neither is front-loaded with what the tool returns.

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 read-only tool with full schema coverage and no output schema, the description covers the credential model reasonably well, and the schema points to get_procurement for `id`. It still leaves gaps on the result shape (raw Markdown? size? truncation?) and on error behavior, which an agent calling a paid, gated endpoint would benefit from knowing.

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 each parameter already carries a detailed description (including how the account cookie and guest token relate to acesso_codigo). The description restates the credential pairings but adds no syntax, format, or interaction detail beyond the schema, 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?

"Reads the Markdown" names a verb and a resource, but the sentence spends most of its words on credential plumbing rather than stating plainly that it returns the Markdown rendering of the tender identified by `id`. It never distinguishes itself from siblings like get_document, get_document_dossier, or gerar_markdown, leaving an agent to guess which retrieval tool produces Markdown.

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?

Usage is implied through access conditions: hold acesso_codigo, or hold avaliacao_codigo plus agent_pass for the sponsored premium, and examples are free. There is no explicit when-to-use/when-not-to-use statement and no named alternative, so the routing decision against get_document or gerar_markdown is left to inference.

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