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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds what the annotations cannot: page size of 100 and that the response carries a next_cursor to feed back as cursor. Since no output schema exists, disclosing the pagination envelope is genuinely useful. It does not say what happens on an invalid or revoked key_id, which keeps it at 4.

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 short sentences, zero filler, and the resource statement plus the security rationale are front-loaded ahead of pagination mechanics. Every sentence carries information an agent can act on.

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 read-only, single-object-scoped list tool with no output schema, the description covers scope, pagination and the practical reason to call it. The remaining gap - what the returned key records contain beyond the cursor - is minor for an enumeration tool.

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 key_id, limit, cursor and purpose are all documented in the schema. The description's "Pages 100 at a time: pass next_cursor back as cursor" largely restates the cursor description, though it usefully ties the limit default to page size. Baseline 3 is appropriate.

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?

"The keys that one API key issued" states the resource and its exact scoping relationship, which separates it in practice from desk_list_api_keys (all keys) and desk_list_api_key_people. It lacks an explicit verb and never names the sibling that handles the unfiltered case, so it stops short of a 5.

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?

"A leaked admin key can make more keys; check here before revoking with cascade" gives a concrete when-to-use anchored to a real workflow (pre-cascade-revocation audit). There is no explicit when-not-to-use or pointer to alternative tools such as desk_list_api_keys for a global view.

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