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

Annotations already cover safety (destructiveHint=false, idempotentHint=true), yet the description still adds real behavioral context: it creates nothing, it returns suggestions rather than acting on them, and a repeat call on an already-read document returns the existing list without re-reading. 'Creates nothing' sits in mild tension with readOnlyHint=false, but the suggestion-generation framing explains the side effect without outright contradicting the annotation.

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 short, front-loaded clauses: what it does, what it returns and how to follow up, and the repeat-call behavior. Every sentence carries information, though the internal vocabulary ('read entity', 'Flows', 'Your SOPs step') compresses meaning at some cost to first-read clarity.

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 states the return ('returns the suggestions') and how to act on it, plus idempotency behavior. For a two-parameter tool with annotations already declaring safety and idempotency, this covers what an agent needs to call it correctly; only the idempotency_key's role is unaddressed and the schema handles that.

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 only 50% (document_id is undocumented in the schema), and the description compensates by specifying its provenance: 'document_id from read entity company_documents.' That is exactly the missing information an agent needs to obtain the UUID, though the idempotency_key parameter is left entirely to the schema.

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: 'Has Sergio read one uploaded company document' with explicit scope ('one', 'for Flows and recurring tasks it describes'). It is clearly distinct from the sibling decide_company_document_suggestion, which it names as the downstream step. It stops short of a fully crisp one-line purpose because the agent-as-actor framing ('Has Sergio read') takes a sentence to parse.

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?

Supplies the prerequisite that document_id comes 'from read entity company_documents' and routes the follow-up explicitly: 'decide each with decide_company_document_suggestion.' It also anchors usage to a concrete workflow ('the setup guide's Your SOPs step'). No explicit when-not-to-use case is given, keeping it off a 5.

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