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

Annotations already declare the write/idempotent/non-destructive profile, and the description adds genuinely new behavioral context: expected_revision concurrency control, owner-wide idempotency_key, the fact that exact retries return the original receipt rather than current state, preservation of anchors and historical pauses, and the tickets:write authorization requirement plus the no-external-comms boundary.

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?

Front-loaded with purpose, then denses in concurrency, idempotency, and authorization in tight sentences with no filler. Slightly dense but every clause carries operational meaning.

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 complex nested-policy mutation with no output schema and no parameter descriptions, the definition covers modes, requirements, concurrency, idempotency semantics, preservation guarantees, and authorization. Describing the receipt return also compensates for the missing output schema; only the deep policy structure is left to the schema.

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 0% schema description coverage the description must carry the semantic load, and it does for the critical fields: mode semantics, expected_revision usage, idempotency_key scope, and the requirement that override supply explicit paused_statuses for all four reasons. It does not unpack the nested thresholds/status_overrides structure, keeping it from a 5.

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 specific verb and resource ('Record a complete project attention override or restore owner inheritance'), making the two operating modes explicit. The name and phrasing distinguish it from get_project_attention_policy and save_ticket_attention_policy, though it never names those siblings directly.

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?

Explains the mode-based condition (override vs. inherit) and routes the agent away from using this call to read state: 'read current policy separately' points at the read sibling. It lacks an explicit when-not statement, but the context is clear enough to select correctly.

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