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

Annotations only flag write/open-world/idempotent, so the description's real contribution is the semantic framing: the proposal is nonbinding, is never a contract, charge, assignment or dispatch, and is subject to human review and possible counter. That is genuinely useful context an agent cannot get from the annotations, though token/auth and idempotency behavior are left to the schema.

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: the first states what is produced and for what input, the second front-loads the safety-critical constraint. No filler, nothing repeated from the schema.

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 15-parameter mutation with no output schema and no annotation detail, the description is thin on operational essentials: it doesn't say what comes back (a proposal id?), that client_request_id is a mandatory idempotency key, or how account/conversation tokens are resolved. The nonbinding framing is complete, but the call mechanics are not.

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 47% across 15 parameters, so the description would ideally compensate. It does name the semantic core (scope, deliverables, timing, location, indicative price) and reinforces the 'indicative, nonbinding' nature of price, but says nothing about the token parameters, the required client_request_id idempotency key, valid_days, confidentiality, or the evidence/cancellation fields.

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?

Names a specific verb (proposes) and enumerates the resource contents (scope, deliverables, timing, location, indicative price) scoped to 'one of your capability requests'. It separates itself from accept/counter/withdraw siblings only indirectly, via 'a human reviews and may counter', rather than naming them.

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?

Usage is implied rather than stated: the proposal attaches to an existing capability request, and the mention that a human 'may counter' hints that a counter path exists. It never explicitly says when to use this versus counter_nonbinding_proposal or withdraw_nonbinding_proposal, nor any prerequisites such as an active request in the right state.

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