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

With no annotations, the description bears full burden. It discloses key behavioral traits: success/failure consequences on edges, growth/pruning rules, and safety axioms (NG1). However, it omits details like idempotency, rate limits, or authentication requirements.

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 concise, with a front-loaded main verb and clear breakdown of evaluation fields. It uses three sentences effectively without redundancy. Slightly more structure (e.g., bullet points) could improve readability, but it is efficient.

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?

Given the complexity (nested object, 3 params, output schema exists), the description covers the evaluation structure and return type (ledger events). However, it lacks details on error handling, idempotency, or prerequisites (e.g., agent must exist). The output schema is mentioned but not described, relying on the schema itself.

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 0%, so the description must add meaning. It thoroughly describes the 'evaluation' parameter structure (task_id, success_score, optional fields). However, 'agent_id' and 'request_id' are not described, though agent_id is self-explanatory. Overall, it significantly aids understanding beyond the schema.

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 clearly states the verb 'Evolve' and the resource 'agent', specifying the input as a task outcome with detailed fields. It effectively distinguishes itself from sibling tools like create_agent or describe_agent by describing a mutation operation unique to this tool.

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?

The description implies usage when a task outcome is available ('Evolve an agent with one task outcome'), but does not explicitly state when to use this over alternatives like compute_efficiency_report or route_task. No exclusions or alternative tools are mentioned.

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