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

Beyond the idempotentHint annotation, the description explains exactly what that means: 'retries are idempotent, stable references prevent duplicate tickets across reprocessed runs.' It also discloses preservation of human edits, non-reset of status/assignee/hierarchy/completion, permission requirements, data visibility (not field-encrypted), and non-actions (never files/pays/sends/publishes). This fully characterizes the tool's side effects and safety profile, complementing the annotations without contradicting them.

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?

The description is dense and front-loaded with purpose, but every sentence contributes meaningful behavioral or usage information. It is longer than average, but this is justified given the tool's complexity, permissions, side effects, and exclusions. It could be tightened by merging some related clauses, but overall it is well-organized and avoids fluff.

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 two-parameter tool with no output schema, the description covers all necessary calling context: preconditions (previewed, completed, expected hash), idempotency and preservation semantics, permission requirements, data visibility, scope, and non-actions. An agent has enough to call it correctly and know what to expect, even without an output schema. The only minor omission is a lack of explicit mention of the return value, but that is not critical given the tool's purpose.

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%; the schema already describes expected_plan_hash as the exact hash from preview_accounting_ticket_sync, and the description reinforces it. run_id has no schema description, but the description provides context that it refers to a 'completed Accounting run.' This adds some meaning but is not elaborate; an agent could still infer run_id is the UUID of the accounting run from the schema format and the description's phrase. The description doesn't add much more than what's already inferable.

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 opens with a specific verb ('Commit') and resource ('a previously previewed completed Accounting run's WRITEOff work plan') to 'stable owner-private Meta Council tickets.' It distinguishes itself from siblings by requiring a prior preview and targeting a specific ticket type, making it clear this is the commit step after preview_accounting_ticket_sync, not a generic ticket create or update.

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?

It sets clear preconditions: the run must be 'previously previewed' and 'completed', and the expected_plan_hash is required. It also explains what it is not for ('never files, pays, sends, or publishes anything') and clarifies scope ('only in-platform planning tickets'). It doesn't explicitly name alternative tools like ticket_create or ticket_update, but the context implicitly routes the agent to use this only for syncing accounting work plans, not general ticket creation.

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