house_style

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

Annotations already mark it readOnlyHint/openWorldHint/destructiveHint false; the description adds that it reads a cached profile and, importantly, will explicitly say when no profile exists instead of returning misleading empty data. That is meaningful behavioral context beyond 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 short, front-loaded sentences: the first states the resource and content, the second adds honesty about the unlearned state. 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?

For a simple read-only tool with an output schema and safety annotations, the description covers the main purpose and the no-profile edge case. It would be stronger if it explained the project/tracker parameters, but they are optional and not blocking.

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?

There are two optional parameters (project, tracker) with 0% schema description coverage, and the description does not mention them or clarify whether they filter the cached profile. It therefore does not compensate for the schema gap.

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 concrete object ('What this team's tickets look like: template, length, labels, habits') and clarifies the mechanism with 'Reads the cached profile.' This clearly differentiates it from sibling learn_conventions, which implies the profile must be learned elsewhere.

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?

The tool is positioned as a cached read, and the phrase 'if none has been learned yet' implies the agent should call it when house style is needed after learning conventions. However, it never names alternatives like learn_conventions or states when not to use it, so guidance is mostly implied.

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