declarations_prepare

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It reveals that this tool returns XML, ANAF URL, Bearer token, and CIF needed by a 'local agent' to proxy an mTLS request. However, it doesn't disclose behaviors like whether this mutates state, whether there are auth/authorization requirements, rate limits, whether the Bearer token is sensitive/expires, or what happens if called without the agent. The 'prepare' wording implies a non-submitting preparation step, but the exact side effects are unclear.

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 two sentences and reasonably front-loaded with the core purpose. The return-value list and operation-param mapping are packed efficiently. One could argue the return values list could be slightly expanded for clarity on shape, but overall it's tight and waste-free.

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?

Given 4 params, 100% schema coverage, no output schema, and no annotations, the description covers the purpose, flows, and return values adequately but not richly. The multi-flow nature (submit/listMessages/download) and the agent-proxy mechanics are non-trivial, and the description does a decent job introducing them. However, without an output schema, the return structure (XML content, URL, token, CIF) is only hinted at rather than fully specified, which is a meaningful gap for a tool whose entire output is consumed by an external agent.

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 documents all parameters well. The description adds value by explaining how the operation param drives flow selection and that downloadId is required for operation=download. It also clarifies that companyId overrides an env var. This adds meaningful context beyond the bare schema definitions, though it doesn't detail the exact format of id (UUID) or companyId beyond what schema states.

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's purpose: 'Prepare a declaration for agent-based submission.' It specifies the verb (prepare), resource (declaration), and the specific goal (agent-based submission). It then lists the return values (XML content, ANAF URL, Bearer token, CIF) and the operation flows. However, it doesn't explicitly distinguish itself from siblings like declarations_submit or declarations_agent_result, though the agent-based proxy nature is implied and somewhat differentiating.

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 explains the operation param with its three flows (submit, listMessages, download) and notes the defaults, but does not explicitly state when to use this vs alternatives like declarations_submit or declarations_agent_result. The agent-based proxy aspect is the distinguishing factor but is not framed as 'use this when...' guidance. No explicit exclusions or alternative tool recommendations are provided.

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