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

Annotations only cover readOnlyHint/destructiveHint, and the description adds critical lifecycle context beyond them: the composition persists for ~30 minutes in 'proposed' status and can be executed once. This persistence and single-use semantics are exactly what an agent needs to avoid stale or duplicate plans.

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 dense sentences, front-loaded with the core action and scope, then inputs, then return shape and lifecycle in descending priority. No filler.

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 9-parameter mutation with nested objects and no output schema, the description covers the return shape, optimization ranking, and persistence/execution lifecycle well. It leaves secondary parameter semantics (location, requester) to the schema, which is acceptable at 100% coverage.

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 100%, so all nine parameters (including the steps/outcomeChain alternative and optimizeFor enum) are already documented in the schema. The description restates optimizeFor values and the steps/outcomeChain duality without adding syntax or format detail, so the baseline 3 applies.

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+resource ('Propose a composition') and immediately defines it as a sequenced DAG of capability instances for a multi-step outcome, distinguishing it plainly from execute_composition. An agent knows exactly what it builds and what it returns.

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?

Routes the agent to the follow-up tool by naming execute_composition and the single-execution constraint, and clarifies the steps-vs-outcomeChain choice. It stops short of explicit when-not guidance (e.g. when to skip proposing and use a search/planner tool instead).

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