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

The annotations already declare a non-read-only, non-idempotent mutation, but the description goes further by disclosing the replacement semantics, the auth requirement (API keys must use 'agent-authoritative'), and the failure mode (403 for editor strategies on an API key). These are behavioral facts the annotations cannot convey.

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?

Purpose is front-loaded, then requirements, sources, constraints and the next step follow in logical order with no filler sentences. It is a dense single block with minor redundancy between 'REQUIRES both fields' and 'selectStrategy is required', which keeps it short of a 5.

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?

With an output schema present, the description need not cover return values, and it does not. For a mutation tool it supplies everything an agent needs: prerequisites, required body fields, credential constraints, error behavior, and the recommended follow-up call.

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 baseline is 3, but the description adds real meaning beyond the schema: where candidateIndex comes from and how selectStrategy interacts with the caller's credential type. Some content ('Body REQUIRES both fields') restates the schema's required array, slightly diluting the value-add.

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 (select) and resource (one candidate from a finished compose/consult ensemble) and pins down the exact effect: a 'whole-candidate replace' of the project's saved composition. That scope statement implicitly separates it from siblings like apply_composition and derive_composition without the agent needing to open multiple schemas.

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?

Provides explicit preconditions (the ensemble must be finished), the provenance of candidateIndex (wait_job(kind="consult") proposals under mode=amend, or the compose winner report), and the follow-up action (render with create_render). It also states an exclusion: editor-merge/editor-replace are unusable on an API key because they need an editor-session token.

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