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

Annotations already declare a safe read, but the description adds real behavioral context the annotations cannot: a 30-minute proposal TTL and the specific failure codes (404 unknown, 410 expired). The expiry semantics materially change how an agent must sequence calls.

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 short sentences, front-loaded with what it does, then error semantics, then usage. Every clause carries information; nothing is restated from the schema or annotations.

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?

No output schema exists, so the description carries the burden of return behavior; it fully covers the error cases but never says what a retrieved composition contains. For a read-by-id tool with known error semantics, this is nearly complete, missing only the payload shape.

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 100%, so the id parameter is already documented as coming from propose_composition; baseline would be 3. The description adds meaning beyond the schema by implying the id is only valid within a 30-minute window, which is a validity constraint on the parameter itself.

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 ('Retrieve a previously-proposed composition by id') and immediately frames the resource as the artifact produced by propose_composition and consumed by execute_composition. An agent can distinguish it from both siblings without opening a schema.

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?

Gives two concrete use cases: inspecting a plan before executing and recovering a plan id after a restart. It stops short of naming the alternative tools (propose_composition / execute_composition) explicitly, so the routing is strongly implied rather than spelled out.

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