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

With no annotations, the description carries the full behavioral burden and does well: it discloses the paid-plan gate, the specific error code and isError shape on failure, that rule count is limited per plan, and that list is capped at 100 rules. It leaves gaps on how deletion behaves (irreversible? error on unknown ruleId?), what list/create actually return, and the concrete per-plan quota values.

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?

Dense single paragraph, front-loaded with the action list, then plan constraints, then per-action parameter needs — no filler sentences. The phrase 'rule count per plan' is telegraphic and slightly unclear, but overall it is efficient.

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?

For a 7-parameter, multi-action mutation tool with no annotations and no output schema, the description never explains what list or create return, nor how to page past the 100-rule cap. It covers invocation requirements well but omits return-shape and sibling relationship context that an agent would otherwise have to infer.

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 86%, so the schema already documents each field, including per-action requirements ('Required for create', 'Required for delete'). The description largely restates that mapping (create: name + fields, optional scopeInboxId/matchFrom/matchSubject; delete: ruleId) and adds only the 'JS' qualifier on regex sources, which is marginal value beyond the schema.

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 set (List, create, delete) on a specific resource (custom extraction rules for the token project), so the agent knows exactly what domain it operates on. It does not explicitly distinguish itself from the related sibling extract_fields, which could be confused with rule management by name alone.

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?

Gives concrete plan-based gating: create needs a paid plan (free tier fails with quota_exceeded), while list/delete work on every plan — a strong precondition signal an agent can act on. It stops short of saying when to manage rules versus call extract_fields directly, so the alternative-selection guidance is incomplete.

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