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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=true, so the description's job is to add context — and it does: omitted terms carry over, revisions after agreement void the agreement and force re-acceptance, and the deal is explicitly nonbinding (no contract, charge, assignment or dispatch). It still omits anything about the response or token/auth needs, but the behavioral delta is 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 dense sentences that front-load the core action and lineage semantics, then the consequence of use, then the nonbinding guarantee. No filler and nothing redundant with 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, the description covers the nonbinding nature and revision lifecycle well but leaves real gaps: no mention of what is returned (e.g. the new revision id), no guidance on the required idempotency key or the account/conversation token choice, and only half the parameters have schema descriptions.

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 should carry more weight. "Omitted terms carry over" is genuinely valuable — it tells the agent this is a partial-update/patch call rather than a full replacement — but none of the individual fields (price, scope_text, deliverables, valid_days, confidentiality, account/conversation tokens) are explained beyond what the schema says.

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?

"Creates a new revision with the terms you change; omitted terms carry over" states a specific verb (creates a revision of an existing proposal) and the patch semantics of the operation. It never names the sibling tools it must be distinguished from (create_nonbinding_proposal, accept_nonbinding_proposal, withdraw_nonbinding_proposal), so routing depends on the reader inferring from the required proposal_id.

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: you counter an existing proposal and only the terms you change need supplying. The warning that "any change after agreement voids it, so both sides must accept again" is a useful prerequisite-style caveat, but there is no explicit when-not (e.g. when to use accept_ vs create_ vs withdraw_) and no named alternatives.

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