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

With no annotations, the description carries the full burden and does so: it discloses that the XML lacks the digital signature (assinado=false, tipo_xml=leitura), enumerates per-key statuses (ok, nao_encontrado, erro), and spells out billing semantics, including that a not-found key is still charged while immediate retries, invalid keys, and errors are not, with per-plan prices.

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 purpose and the signature caveat come first, followed by status codes and pricing, so the most decision-relevant information is front-loaded. The pricing sentence is dense with parenthetical figures, but each detail supports the cost-consent decision, so it 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?

A schema for the output exists, so return values need not be explained, and the description still covers statuses and the signature caveat. Combined with the plan/balance prerequisite and the consent gate, an agent has everything needed to call this correctly and to explain the cost to a user.

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 adds meaning beyond the schema by explaining the cost that confirmo_custo gates and the balance deduction (3 consultations, or 2 for Enterprise), giving the agent context it needs before asking the user for consent.

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 states a specific verb and resource: it returns a read-only copy of the XML for exactly one NF-e (model 55), identified by a 44-position access key, without a digital certificate. It also draws the scope boundary (one key, not a batch) and clarifies that the result carries no signature, so an agent can distinguish it from every listed sibling, none of which deal with XML.

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 a clear context for use and an explicit exclusion: the copy is for reading, not for validating schema or signature. It also states the prerequisite of having a plan or balance. It does not name an alternative tool for obtaining signed XML, but no sibling offers that capability, so the gap is minor.

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