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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the bar is lower, yet the description adds real value: it discloses the visibility scope (own children vs. full org for admins) and explicitly warns that the raw credential is never returned. It omits pagination or result-size behavior for a list endpoint.

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?

It is a single tightly packed sentence with the key facts (endpoint, scope, returned fields, credential exclusion) front-loaded. The em-dash parenthetical listing the six output fields is dense but earns its place; slightly run-on structure keeps it from 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 no parameters, no output schema, and simple annotations, the description compensates well by enumerating the returned fields (id, label, scopes, status, depth, expires_at) and the visibility rules. The only missing element is behavior for large result sets (pagination/limits) on a list endpoint.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no filtering inputs are needed beyond session context, and adds nothing misleading about 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 delegated child keys) plus the underlying endpoint (GET /delegations). The phrase 'this key's own direct children' precisely scopes the result and implicitly distinguishes it from org-wide or sibling 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?

Gives clear context for use: it is a read-tier operation, and it explains that an admin session returns every delegated key in the org while a non-admin sees only direct children. It does not explicitly mention alternatives such as revoke_delegation or when not to call it, so it falls short of a full 5.

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