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

Annotations declare readOnly/idempotent/non-destructive and the description's 'READ-ONLY' is consistent, not redundant filler. It goes well beyond the annotations by disclosing ownership-conditional behavior (config health only for departments you own), the not-found collapse, and precisely what the health check reports (dropped/refused members, deliberately omitted package parts).

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 dense paragraph, front-loaded with what is read and followed by access and failure semantics. Every clause carries information, though the long em-dash-heavy middle sentence is harder to parse than it needs to be.

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?

An output schema exists, so return-shape explanation is optional, yet the description still covers scope, ownership gating, failure modes, and the optional expensive sub-operation. Nothing needed to call it correctly is missing.

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 baseline is 3, but the description adds real meaning: it explains what config health is for ('fix it before connecting') and that it is the slower part of the call because it reads each member agent, which justifies the default-true-for-owners behavior.

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 ('Read one department you can access') and enumerates exactly what is returned: members with alias/role/agent slug, topology, report_instructions, MCP connect address, plus ownership-gated config health. An agent can distinguish this from findagent_list_departments or findagent_get_org without opening a schema.

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?

Clearly scopes the reachable set (personal departments you own, org departments of orgs you belong to) and pins failure semantics (inaccessible, archived, and unknown slug all collapse to the same not-found). It never explicitly names findagent_list_departments as the discovery alternative in prose, but the access boundaries give strong usage context.

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