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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, closed-world), so the bar is lower; the description still adds real value by disclosing the auth requirement (OAuth only, API keys cannot manage keys) and that key creation is web-only and shown once. It omits pagination or result-size behavior, which is the remaining behavioral gap.

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 tight, front-loaded sentences with no filler; the listing scope leads and the constraints follow. The final clause about keys being shown once is peripheral to a listing operation and slightly exceeds what is needed here.

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 output schema, the description compensates by naming the returned fields (name, prefix, company, last use), and it covers auth prerequisites and the absence of an API-side key-creation path. For a zero-parameter read tool, nothing an agent needs before calling is missing.

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 cannot add parameter meaning, and it correctly does not invent any; it instead enumerates the returned fields, which is useful although not a parameter concern.

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 the workspace's API keys') and immediately names the return fields (name, prefix, company, last use). It also implicitly separates itself from the only other key tool, keys_revoke, and from non-existent create/update key tools by stating keys are created only in the web app.

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 operating context: it works over a signed-in (OAuth) connection and an API key cannot manage keys, plus it redirects key creation to the web app. It does not explicitly name keys_revoke as the alternative for key lifecycle operations, so the when-not guidance is present but not fully routed.

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