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

With no annotations, the description carries the full disclosure burden, and it does well: it states stability ('stable page'), field precision ('exact seconds_count'), and important semantics ('report-only disclosed_linked_seconders coverage', 'never a gate'). It also spells out the pagination contract. It does not cover auth, rate limits, or full response shape, but the disclosed behaviors are substantive.

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?

Two tight sentences with no filler. The core purpose is front-loaded, and the field semantics plus pagination contract are compressed into the second sentence without losing 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?

For a five-parameter list endpoint with no output schema and no annotations, the description is incomplete: it omits the meanings of since, limit, and stage, and gives no guidance on selecting this tool among many siblings. It covers pagination and row-level field semantics, but an agent would still be uncertain about the full request and response contract.

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 40%, covering q and cursor, while limit, since, and stage lack descriptions. The description adds meaningful meaning only for cursor via the pagination directive; it says nothing about how q filters, what since means, how limit behaves, or how stage selects pipeline phases. It does not compensate for the low schema coverage.

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 identifies the resource ('a stable page of proposals') and its scope ('at every stage of the pipeline'). It does not explicitly differentiate from siblings like get_proposal or list_measurements, but it conveys a distinct paginated, cross-stage listing purpose.

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 only usage guidance is the pagination instruction to follow next_cursor until has_more is false. There is no mention of when to prefer this tool over sibling list/detail tools, nor any exclusions such as 'use get_proposal for a single proposal' or 'use list_measurements for measurements.'

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