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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds material context beyond them: auth requirements (user session or B2B token), error semantics (401/403 wrong auth), empty-list behavior, and the shape of returned fields (ids, names, owner, visibility, categories, config).

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 core listing behavior and the appId switch are front-loaded, and every clause carries information. It is dense with parenthetical endpoints and error codes, which is slightly heavy but not redundant.

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 read-only list tool with no output schema, the description covers scoping, the account-vs-app ownership nuance, auth, error behavior, and return fields — everything needed to call it correctly without opening 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?

Schema coverage is 100%, so the schema already explains limit, offset, category, and visibility. The description still adds value on appId by noting it requires app management rights and that B2B tokens always use the app-scoped form, but it does not add anything for the remaining parameters.

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 ('List AI agents') plus the backing endpoint (GET /v2/agents), and immediately distinguishes the appId-scoped variant (GET /v2/apps/:appId/agents). It also clarifies the account-level ownership model, so an agent won't confuse this with per-app listing tools.

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?

Explicitly states the default behavior (own agents plus public), the condition that changes it (pass appId, which requires app management; B2B tokens always use this form), and routes public-agent use to the named alternatives ethora-agent-try and ethora-agent-clone, noting they cannot be edited here.

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