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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: it is hosted by the platform (no user credentials required), requires prepaid credit per query, and explicitly states the data is not confidential and subject to LGPD responsibilities. These details go beyond annotations and help the agent understand operational constraints and legal obligations.

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 concise and front-loaded, starting with the core purpose ('SEFAZ AL: NFC-e, consulta em fonte oficial') followed by operational and legal details. Every sentence adds value, and there is no fluff or redundant information. It is appropriately sized for the tool's simplicity.

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 simple tool with one parameter and no output schema, the description covers the operational context (payment, credentials, LGPD) and states it queries information. However, it omits any explanation of what the parameter should contain and what the response will look like. While annotations cover safety, the lack of parameter details and output description leaves gaps for a first-time caller.

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?

The schema has one required parameter 'nfce' (string) with 0% description coverage. The description does not explain what value the 'nfce' parameter should contain (e.g., access key, invoice number, format). While the parameter name is suggestive, no format or example is provided. The description fails to compensate for the lack of schema documentation, leaving the agent to guess the expected input.

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 clearly states the tool queries NFC-e data from SEFAZ AL, an official Brazilian tax source. The verb 'consulta' (query) and specific resource 'NFC-e' from 'SEFAZ AL' leave no ambiguity about what the tool does. It also contrasts with generic sibling tools like 'authenticate' or 'show_version', making its unique purpose obvious.

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 provides operational context (hosted platform, prepaid credit, no credentials) but gives no explicit guidance on when to use this tool versus alternatives. There is no mention of use cases, exclusions, or when not to use it. Since sibling tools are generic platform utilities, the lack of alternatives is understandable, but the description still offers no decision-making support for tool selection.

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