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

Annotations already cover read-only/idempotent/non-destructive, so the safety profile is redundant, but the description adds genuinely new traits: cost is free and not counted against tasks, and proposals carry a 48 h expiry. It does not describe return format or ordering, but the added cost/expiry context is meaningful.

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?

Front-loaded with the read-only/cost banner and the core action, then use cases. Compact and structured, with only mild repetition of the annotations in the opening clause.

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 two-param, zero-required, read-only list tool with a fully documented schema and no output schema, the description supplies everything needed: what comes back (preview, expiry), when to call it, both modes, and cost.

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 100% and both properties already document themselves; the description largely restates the proposal_ids semantics rather than adding syntax or limits beyond 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 ('Lists writes that were proposed but not yet approved') and names the concrete payload returned (preview and expiry). It also distinguishes the dual mode (pending-only vs. proposal_ids for any status), so an agent can tell it apart from approve_proposal/reject_proposal and the write siblings.

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?

Gives explicit triggers: 'the user asks "what is waiting for my approval"' or 'after a tool returned proposal_pending', and a separate trigger for the proposal_ids variant ('use it when the user asks whether a change went through'). Both when-to-use paths are spelled out.

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