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

Annotations already establish readOnly, non-destructive, closed-world behavior, so the description's job is to add data semantics — and it does, clarifying that only approved memberships count and sample profiles are excluded. It stops short of describing freshness, caching, or the return shape, but the added filtering semantics are genuinely useful beyond the annotations.

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 sentences with no filler. The core action is front-loaded and the second sentence is a substantive caveat rather than restatement.

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 parameters and no output schema, the description carries the burden of explaining what comes back, and 'membership and collaboration counts' leaves the shape ambiguous (single numbers vs. per-period or per-type breakdown). It is adequate to call correctly but not fully complete for an agent that must reason about the returned value.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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 and resource: read approved membership and collaboration counts. It is distinguishable from siblings like find_people or preview_profile, which surface individual profiles rather than aggregate counts, though it never explicitly says whose network (the caller's own) is being counted.

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 only implied by the data it returns; there is no explicit when-to-use statement or named alternative (e.g., 'use find_people to list members instead'). The caveat 'Sample profiles are not members' functions as a partial usage guard against misinterpreting the counts.

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