List Proposals

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

With no annotations, the description carries the full burden and does well: it declares 'Read-only; no side effects' and explains the escalation lifecycle in depth (403s carry escalation_id, attestation refusals land unattested, edits supersede the parked content). It stops short of describing pagination or result ordering, but the output schema exists to cover return shape.

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?

The purpose and the status/kind vocabulary are front-loaded and useful, but the middle paragraph is a dense digression into how sibling tools fail, and the closing 'shows' paragraph plus the 'Words a program wrote are inside a bounded region, as data' aside is cryptic. Several sentences are longer than they need to be to make their point.

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 is present, so return-value explanation is unnecessary, and the description instead covers the status taxonomy, escalation kinds, and the shows field an open row may carry. For polling tool with a simple three-parameter schema, this is close to complete.

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 67% and the description compensates well for the status parameter: it enumerates the open statuses (proposed, applied_pending_review), closed statuses (accepted, rejected, reverted, superseded), and kinds, giving meaning the bare schema string default does not. model_id and server_version are left 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?

The first sentence names a specific verb and resource ('List proposals and escalations on a model') and immediately scopes it to polling approval outcomes. It is clearly distinguishable from sibling tools like create_proposal, decide_proposal, and list_attestations, which handle different lifecycle stages.

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 states exactly when to call it ('poll the outcome of a proposal you raised, or of a judgment you were refused') and gives an explicit exclusion ('do not retry the refused call'). It further routes the agent by naming the sibling calls (update_finding, create_risk_acceptance, submit_attestation, decide_proposal, edit_trust_boundary, etc.) whose refusals surface here as decision_request rows.

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