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

Annotations only declare readOnlyHint=true; the description adds real behavior: what is counted (planned and split lines), that the number equals the reassignment count, and that foreign or nonexistent categories return not-found rather than zero. It stops short of describing rate limits or the exact response shape, which keeps it at a 4 rather than a 5.

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 tight sentences, front-loaded with what is counted, then the workflow reason, then the error condition. No sentence repeats the name, the schema, or the 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?

For a one-parameter read tool with no output schema, the description covers counting semantics, workflow purpose, and failure behavior, which is nearly everything an agent needs. The only minor gap is that it does not say the result is a single numeric value explicitly.

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 100% and the single categoryId parameter is already documented as a UUID from get_categories, so the description adds no format or sourcing detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 (count) and resource (transactions filed under a category), plus the non-obvious inclusion scope: planned transactions and split lines are counted. An agent can immediately tell this apart from listing or spending tools because it explicitly returns a count that would be reassigned rather than a list or aggregate.

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 an explicit when-to-use rule: "Call it before delete_category," and explains the decision it informs (a category with transactions requires replaceWithCategoryId). It also states the not-found condition for missing or unauthorized categories, so there is nothing left to infer.

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