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

Adds behavior annotations do not carry: the link expires after 10 minutes and the call requires an X-Mako-Key header. Expiry and auth requirements are exactly the sort of context an agent needs and cannot infer from readOnlyHint/openWorldHint. The 'mint' verb sits in mild tension with readOnlyHint, but generating an ephemeral URL does not modify stored state, so it is not a genuine contradiction.

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 sentences, no filler, and the most important constraint (short-lived link) is front-loaded right after the purpose.

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 one-parameter tool with no output schema, the description covers purpose, auth, and expiry. It only lightly implies that the return value is the URL itself rather than naming the returned field, which is a minor gap.

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 100% and the single parameter is documented ('From list_deliverables'), so the schema already does the work. The description adds no further parameter detail; baseline 3 applies.

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: 'Mint a download link for one deliverable.' An agent can distinguish this from list_deliverables (which supplies the id) and from the other siblings, which operate on brands/clients/orders.

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 timing guidance and an explicit exclusion: 'fetch it when the human is ready to use it rather than in advance.' The schema note 'From list_deliverables' implies the required prior step, but no alternative tool is named for comparison.

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