Follow overlap

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

Annotations already declare readOnly and openWorld, so safety posture is covered. The description contributes useful provenance ('archive-derived edges') and names the returned metrics, but omits cost/pagination behavior implied by the 1-40 max_pages bound, which matters for a potentially expensive two-sided fetch.

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 front-loaded sentence that states inputs, options, and outputs with no filler.

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 50% parameter coverage, the description should explain the response shape more concretely (counts, list format) and clarify how max_pages affects results. It names the metrics but leaves the agent to guess the returned structure and depth limits.

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 50%: 'a'/'b' and 'kind' are self-evident or enum-bounded, but 'max_pages' is undocumented in both schema and description, and the description offers no syntax or format guidance beyond what the schema gives. Baseline 3 for partial coverage where the description adds little.

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 gives a specific verb (compare) and resource (two accounts' followers/following) and even names the outputs (shared accounts, Jaccard similarity). It does not distinguish itself from the close sibling ca_account_relations, which likely also deals with follower/following edges.

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?

No guidance on when to use this comparison tool versus the sibling ca_account_relations or ca_find_people, and no prerequisites noted beyond the vague 'archive-derived edges' provenance. An agent must infer that this is the overlap/intersection tool rather than the listing tool.

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