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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds real value beyond that by disclosing the redaction rule (L2 document bodies are never leaked) and the provenance fact that proposals are human-applied. It stops short of describing pagination or ordering behavior.

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 short sentences, front-loaded with the core purpose and the leak constraint, with no padding. The second sentence is somewhat telegraphic but still earns its place by pointing at an alternative.

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?

An output schema exists, so return values need not be explained, and annotations cover the read-only nature. However, three undocumented filter parameters with no enum on status leave an agent guessing at invocation details, which is a meaningful gap for a listing tool.

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 0%: limit, status, and doc_key have no descriptions in the schema and the description text does not mention any of them. An agent must guess whether status is an enum-like string, what doc_key accepts, and what limit defaults mean beyond the schema default of 50.

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 uses a specific verb ('List') with a concrete resource ('proposals and arena vote scores') plus a scope constraint ('without leaking L2 document bodies'), so the agent knows exactly what it returns. It does not, however, differentiate itself from close siblings such as vote_on_proposal or propose_document_change.

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?

'Proposals are human-applied. Use request_human_review for a pending item.' gives one routing hint toward a sibling, but it is ambiguous about when this tool should be called instead. No guidance on when to use it versus propose_document_change, vote_on_proposal, or review_task.

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