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

The description discloses the internal steps and the shape of the result, which adds real value. But the annotations declare readOnlyHint=false and idempotentHint=false on what reads like a read-and-analyze operation; the description never explains what the non-read-only side effect is (does the scan persist a record? does it consume quota or require the account to be a member?). That unexplained mismatch is the main behavioral gap.

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?

Front-loaded purpose sentence followed by a scannable when-to-use block and a returns line. Every sentence carries information; nothing is repeated from the schema or annotations.

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?

There is no output schema, and the description compensates by enumerating the return fields (overall_score, is_disqualified, disqualify_reasons, component scores, verdict). Parameters are fully covered by the schema. What's missing is cost/latency expectations and what happens on an invalid or inaccessible group_id.

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% with only 3 parameters, all documented in the schema itself (including the group_id id-vs-platform-id dualism and the account_id/in_workspace overrides). The description adds no parameter-level meaning, so the baseline of 3 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?

The description opens with a specific verb+resource ("Scan a group") and explains both the mechanics (fetches recent messages, analyzes activity/spam/engagement) and the output (quality score, verdict). This clearly distinguishes it from siblings like group_preview_messages, which only previews messages rather than scoring them.

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?

It gives explicit timing ("After finding groups with group.search", "Before deciding which groups to join"), naming the sibling that feeds it. It doesn't state exclusions or contrast with group_preview_messages/group_get_invite_link, so it's clear but not fully exhaustive.

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