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

Annotations only declare the generic non-read/non-idempotent profile; the description adds real operational context beyond them: one pending request per kind, the new value must exceed the current limit, the organisation is notified on decision, and billing permissions are required. It also discloses that a human reviews the justification, which is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Two dense sentences that front-load the purpose, then usage, then constraints; nearly every clause carries actionable information. Slightly run-on and packs several ideas per sentence, which costs it the top mark.

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 still conveys that this is an async, human-reviewed request whose outcome arrives via notification, and it points at get_registry_storage and list_limit_requests for state. A brief note on what a submission returns (e.g. a request id or pending status) would make it complete.

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 baseline is 3, but the description adds meaning the schema lacks: the 8 GB default playground memory budget and the fact that registry storage is measured per registry project, plus the human-review nature of the justification. It does not restate the per-kind parameter requirements, which the schema already handles.

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+resource ('Submit an organisation limit-increase request for review by the Ankra team') and enumerates exactly the three limit kinds it covers, which lets an agent separate it from siblings like request_provider_quota_increase and list_limit_requests without opening 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?

Gives explicit trigger conditions (create_playground/resize_playground refusing for budget headroom, user asking for a bigger AI allowance, registry full), names the prerequisite read tool (get_registry_storage), names the alternative (set_registry_retention) and states when it is insufficient, and adds a negative instruction ('Do not retry the refused order or push').

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