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

Beyond the annotations (destructive, non-idempotent, not read-only), the description adds real behavioral facts: single-use ("goes once"), a 24-hour validity window, a precondition that the proposal must still hold, and that it is applied under the person's name. What is missing is what exactly gets revoked, and what happens when the proposal is stale or expired.

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 sentences, but the final sentence largely repeats the first ("the person saw and said yes to" vs "the person has seen and said yes to in this conversation"), and indirect terms like "that line" cost the agent decoding effort without adding information.

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 an irreversible mutation the description covers expiry, single-use, and authority, and an output schema exists so return values need not be explained. Still missing are permission requirements, failure behavior for expired/stale proposals, and any statement of what the change actually alters (who loses access).

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 parameters are documented in the schema (including the project fallback rule). The description only restates that the change is keyed by the proposal id; it adds no format, constraint, or error-handling semantics beyond structured data. Baseline 3 is appropriate.

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 verb+resource are present ("Makes an access change (who sees what)"), and it is scoped to a previously agreed proposal. But the phrasing is circumlocutory — "the line saying what it opens or closes" is never defined — so an agent must decode rather than read what it does, and no sibling (set_access, send_change, agreed) is named in the description body.

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?

"For a change the person has seen and said yes to in this conversation" gives a positive usage condition. However there is no explicit when-not, no routing to set_access for creating a proposal, and no guidance for the common failure cases (proposal expired, person changed their mind, no proposal exists).

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