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

Adds real value beyond annotations: it explains retry identity ("exact identity and body identify retries"), which elaborates the idempotentHint, and clarifies what the call does not imply ("without read attestation or human acceptance"), contrasting with confirm_acceptance. However, with destructiveHint=true, it never says what is destroyed or invalidated, or what happens on a baseRevision 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 tight sentences, front-loaded with the recorded payload before the identity and return details. The parameter list sentence is slightly clunky but every clause carries 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?

Covers the return value at a high level and the absence of output schema is acceptable, but for a destructive, revision-guarded mutation with nested objects, it omits the important operational behavior: conflict handling on stale revisions and what state the destructive operation affects.

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 50%, so the description's naming of clientId, baseRevision, purposeRevision, and snapshotId and its retry-identity rule is useful. But the revision precondition (what baseRevision/purposeRevision must match, and conflict behavior) and the meaning of resultRefs and checkBack triggers are left entirely to 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 concrete verb ("Records") plus what is recorded (summary, resultRefs, blockers, checkBack or stopReason), and adds a negative differentiator ("Does not create a scheduler"). It stops short of naming the sibling that does create the scheduler or explaining what "done for now" means at the workflow level, so it is clear but not fully disambiguating.

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?

The only routing guidance is the exclusion "Does not create a scheduler," which implicitly points to purpose_set_check_back/set_check_schedule. There is no explicit when-to-use versus purpose_renew, purpose_release, finish_turn, or working, and no stated preconditions such as needing a current revision.

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