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

Annotations already declare readOnlyHint/destructiveHint=false, yet the description adds real context: the 'live rule would book' count, the exclusion logic, and the fact that accepting produces a draft that books nothing until human approval. That downstream consequence is information an agent cannot get from 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, front-loaded with the core purpose, and the field enumeration and exclusions are packed efficiently. The single long listing sentence is dense but every element is useful.

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?

An output schema exists, so return shape need not be explained, and the safety profile is strong. The remaining gap is parameter guidance (limit, companyId), which leaves an agent guessing about pagination.

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?

With only 50% schema coverage, the description needs to compensate but does not mention either parameter. The companyId schema text is boilerplate ('UUID value wrapper.') and limit (0-20) is completely undocumented, so the agent gets no guidance on scoping or page size.

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?

Names a specific verb (list) and a precisely characterized resource: merchants repeatedly hand-categorized that are candidates for a rule. It even enumerates the fields each suggestion carries, so an agent knows exactly what comes back.

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 explicit exclusion criteria (already-covered, split-across-categories, and declined merchants are omitted) and names the follow-up tool transaction_accept_rule_suggestion with the caveat that it only drafts a rule. It does not, however, contrast this with the many nearby siblings such as transaction_get_list_rule_proposals or transaction_get_list_rule_gap_observations.

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