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

Annotations already declare readOnlyHint=true, and the description reinforces this ("a read-only search"), so the bar is lower. It adds genuinely useful non-obvious context: the endpoint is POST despite being a read, and pagination is cursor-driven via meta.next_page. It does not describe result shape or default/maximum page size behavior, but that is covered by the schema.

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?

A single front-loaded sentence plus a paging clause, with no filler. The parenthetical gloss is longer than a bare definition but earns its place by explaining a domain-specific term the agent cannot infer.

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 names the primary return concept (attribute keys, usable as custom_attributes) and reveals the pagination field (meta.next_page) needed to iterate. Safety is handled by annotations. Only the filter semantics of kind/name/department_id are left entirely to the schema, which is acceptable at 100% coverage.

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%, so the schema already documents kind, name, page, page_size and department_id with types, ranges and defaults. The description's only parameter-related contribution is restating the page/meta.next_page pattern, which the schema already says. Baseline 3 is correct.

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 concrete verb and resource ("List the custom attribute keys") and then defines the resource in-line ("placeholders such as a grade or date that credential designs and e-mails merge in"), which is exactly the disambiguation an agent needs for an unfamiliar domain term. No sibling tool searches attribute keys, so there is no plausible confusion with the other search_* tools in the list.

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 a clear reason to call it ("useful to know which custom_attributes a credential can carry") plus an operational instruction for paging ("pass meta.next_page as page"). It does not state when not to use it or name a competing tool, which keeps it short of a 5.

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