spv_sync_prepare

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

Adds auth context beyond the annotations: mTLS with the qualified certificate is required and the OAuth token is rejected by SPVWS2, which is a crucial constraint for the calling agent. It also discloses the payload (URL + pending PDFs) rather than only repeating the annotation hints; it doesn't contradict readOnlyHint=false, since preparation likely records sync state.

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?

Three tight sentences, front-loaded with the step/purpose, then the call mechanics, then the handoff. Every sentence adds information with no filler.

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?

With no output schema, the description correctly explains what is returned (the listaMesaje URL and pending PDFs) and the required auth. The only minor gap is the shape and structure of the pending PDFs payload, but the essentials for correct invocation are present.

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 days and companyId are already fully documented in the schema. The description adds no extra meaning about these parameters (e.g., defaulting behavior or how companyId interacts with the env var), 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?

States a specific verb and resource: 'Step 1 of an SPV inbox sync' that returns the ANAF listaMesaje URL plus pending PDFs. It is clearly distinguishable from the sibling spv_sync_agent_result, which is named as the relay step.

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?

Gives the operational context: the returned URL must be GET with the qualified certificate (mTLS), and the response must then be relayed via spv_sync_agent_result. It clearly places this call in a two-step flow, though it does not state what to do if the flow is out of order or what happens on repeated calls.

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