Mint a share link

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation profile is known; the description adds the non-obvious detail that this endpoint has no server-side dry run and that nothing is sent without confirm. That is real value beyond the structured fields. It still omits return behavior (link URL/expiry), rate limits, and any auth requirements.

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 short sentences with the resource and endpoint front-loaded, then the safety constraint. The parenthetical about no server-side dry run is compressed but still readable, and there is no filler.

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 mutating tool with a nested body object and no output schema, the description covers the write-gating behavior well but leaves the agent without information on what the returned link looks like, how ttlHours defaults, or what the confirm:false preview contains. Adequate but with meaningful gaps for a creation operation.

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 50%, so the schema documents confirm and idempotencyKey but leaves id and body.ttlHours undescribed. The description reinforces the confirm gate but adds no meaning for id, for ttlHours (no default or expiry semantics stated), or for the nested body shape, so it does not compensate for the coverage gap.

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 share link') and even names the underlying endpoint POST /v1/reports/{id}/share-links, so the agent knows it creates a link for a specific report. It is clearly distinguishable from shareLinks_list and shareLinks_revoke by the verb alone, though it never explicitly names those siblings.

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?

The description gives one concrete operational rule — the write is not executed unless confirm: true — which is genuine usage guidance for calling it. It says nothing about when to prefer this over shareLinks_list/revoke or about prerequisites such as report existence or permissions, so usage is only partly covered.

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