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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, yet the description adds real context: no credit spend and no record mutation, plus a required confirmed=true gate. It does not explain why a read-only, zero-cost call still needs confirmation when the schema says confirmed is for 'this change or credit use', leaving a small ambiguity.

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?

Four short, front-loaded sentences with the core capability first and the guardrail last. Minor waste in 'Retrieves data without changing records', which largely repeats the readOnly annotation.

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?

No output schema exists, so the description must convey the return shape; 'say which are prospects and where they are' is vague about what 'where' means (list membership? tags? counts?). It also doesn't reconcile the confirmed=true requirement with the read-only, no-credit claim.

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 50% with a nested body object, so the description must carry weight. It restates the 500-ID cap and calls out the confirmed flag, but says nothing about record_type (property/person/company) and does not clarify that record_ids may be prefixed strings or bare numbers.

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?

Specific verb+resource ('Check prospect state') plus scope ('up to 500 record IDs, say which are prospects and where they are'). However, it never differentiates itself from the near-identical sibling dealmachine_get_prospects_by_record, which an agent could easily pick instead.

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?

It gives one intent ('Use it to avoid duplicate adds'), which implies usage before dealmachine_prospect_add, but no explicit when-not condition and no named alternative. With dealmachine_get_prospects_by_record and dealmachine_prospect_get in the sibling list, the agent is left to infer which one applies.

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