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

Beyond the destructiveHint/idempotentHint annotations, the description adds real behavioral context: 'exact identity and body identify retries' explains the concrete idempotency mechanism, and 'without read attestation or human acceptance' tells the agent no confirmation or read-back step is required. What it omits is the consequence of cancelling (does it free the participant, drop pending work?) and error behavior on revision mismatch.

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?

Three compact sentences with the verb and target front-loaded and no filler. The final sentence is jargon-heavy ('revision-bound command result', 'read attestation') but each sentence carries distinct 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 a destructive, nested-object command with no output schema, the definition covers retry identity, revision binding and the absence of an acceptance step. It stops short of the room_id parameter, why contractRevision is required in practice though absent from the schema's required list, and what happens when the revision is stale or no check-back exists.

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 50%, with clientId and room_id documented but baseRevision, purposeRevision, snapshotId and contractRevision bare. The description names four of them and adds retry semantics for clientId, but the semantically pivotal contractRevision is asserted in sentence one yet never explained or included in its own enumeration, and room_id is never referenced at all.

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 description names a specific verb ('Cancels') and resource ('check-back declaration'), which cleanly separates it from the sibling purpose_set_check_back. It is slightly muddied by pulling contractRevision into the first sentence while the second sentence lists a different set of parameters, but an agent can still tell what the tool does.

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 only implied: it is a cancellation of an existing check-back, and the concurrency constraint hints at stale-revision errors. There is no explicit when-to-use versus purpose_set_check_back, no statement of preconditions (must a check-back exist?), and no guidance on what to do when the revision has moved on.

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