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

Adds substantial behavioral context beyond annotations: it confirms read-only execution ('without writing'), discloses permission requirements, and reveals privacy risks (tickets not field-encrypted, source-derived snippets may be exposed to tickets:read after commit). It also warns about large ticket counts and suggests confirming with the owner—details annotations do not capture. No contradiction with readOnlyHint/idempotentHint/destructiveHint.

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 longer than average but every sentence contributes: purpose, permissions, privacy risk, and item-count caution. It is front-loaded with the main action and reports before caveats. Could be tightened with bullet points, but the density is justified given the safety-critical context.

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 preview tool with an output schema, the description covers what is needed: inputs (run_id context), expected outputs (creates/updates/unchanged), edge cases (human-edited fields, identity conflicts), prerequisites, and operational warnings. Combined with output schema and annotations, the agent has everything to invoke correctly.

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?

With one parameter (run_id) and 0% schema description coverage, the description compensates by specifying it refers to a 'completed owned Accounting run's WRITEOff work plan.' This adds constraints beyond the raw uuid format, clarifying which run is valid. Since the parameter is singular and self-contained, the description fully covers its semantics.

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 states a specific verb ('Preview, without writing') and resource ('WRITEOff work plan' mapping to 'stable Meta Council tickets'), clearly distinguishing it from sibling tools like sync_accounting_tickets. It enumerates the exact reports produced (creates, updates, unchanged tickets, preserved fields, identity conflicts), leaving no ambiguity about scope.

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?

Explicitly instructs 'Preview before committing' and warns against committing a 'board-flooding sync' when item count is large, indicating when to use and when not. It also states required permissions (accounting:read, tickets:read) and notes that tickets:write satisfies the read grant, providing clear eligibility for use.

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