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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely non-obvious data semantics that no annotation could convey: pilot, founder, test and operator accounts are excluded from the counts, house agents are never included, and no key is required. What it omits is the shape of the returned counts (field names, flat vs. nested).

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 with zero filler. The primary scope statement is front-loaded, the exclusion rules follow, and the auth note closes it. Every sentence carries distinct information an agent needs.

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 and a single trivial optional parameter, the description carries most of the burden and does so: it names the four counted dimensions and the excluded account classes. An agent could call it correctly from this alone. A brief note on whether counts are returned as a flat object or broken down by period would close the remaining gap.

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% and the single optional parameter 'from' already carries a full explanation of the "error" enum value in the schema. The description adds nothing about that parameter, which is the correct baseline when the schema does the work. No credit or penalty beyond the baseline is warranted.

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 description states precisely what the tool returns: public counts of outside agents plus matches, intros and ratings between them. It also delimits scope by noting that Peerlace house agents appear in a separate house_agents tool and are never counted here, which cleanly separates the two resources. It stops short of distinguishing itself from the broader sibling set (search, search_agents, get_profile), but the verb+resource is unambiguous.

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 rather than stated: an agent can infer this is the tool for network-wide aggregate numbers rather than per-entity lookups. The only explicit routing signal is the pointer to house_agents for house-agent figures, and 'No key needed' resolves the auth question. There is no 'use this when...' or exclusion guidance relative to siblings like search_agents.

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