aism_users_list

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely useful behavior beyond them: it discloses what is deliberately excluded (no password hashes or tokens), that pagination headers are returned, and the exact capability requirements plus a version prerequisite. It stops short of describing ordering or total-count behavior.

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 tight sentences, front-loaded with what is returned and followed by the security guarantee and prerequisites. The 'companion 1.5.0+' clause is a bit opaque, but every sentence carries information.

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 does the necessary work of enumerating returned fields and explicitly ruling out secrets, which is the key concern for a user-listing tool. It is slightly incomplete on filter behavior and default-site handling, but adequate for correct invocation given the annotations.

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 only 60%, with page and per_page carrying no descriptions, yet the description says nothing about filtering or paging inputs. It mentions 'pagination headers' in the response, not the per_page/page parameters, so the description does not compensate for the coverage gap even though filters (role, site, search) are the main lever for narrowing results.

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?

Names the specific resource (user accounts) and enumerates the fields returned (login, email, roles, registration date, sessions, application passwords), so the agent knows exactly what the call yields. It does not explicitly differentiate itself from the similarly named siblings aism_user_get or aism_user_quarantine, leaving that to the list/get naming convention.

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?

Usage is implied by 'Review user accounts' and by the stated prerequisite capabilities (users:read and list_users), which tells the agent when the call can succeed. There is no explicit statement of when to use this versus aism_user_get for a single user, nor any exclusion or alternative routing.

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