learn_conventions

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds genuine value beyond them: it discloses that the operation is slow (a few hundred API calls) and that it caches the result. This latency and persistence context is not conveyed by the annotations and helps an agent budget for cost.

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 front-loaded paragraphs where each earns its place: purpose first, then cost/frequency, then the two parameter modes. Slightly long but well organized 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 5 parameters, no schema descriptions, and two distinct operational modes, the description explains the modes well but leaves keep, project, and tracker unexplained. An output schema exists so return values need no coverage, but the unexplained parameters leave a real gap for a tool this complex.

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 schema description coverage at 0%, the description carries the burden and does explain sample (the cap on tickets read) and from_tickets (take examples as given vs mine the tracker). But keep, project, and tracker are left entirely unexplained, so the description compensates for only 2 of the 5 parameters.

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 states a specific verb+resource ('Learn how this team writes tickets, and cache the result') that clearly distinguishes it from sibling tools that review slips (review_draft, review_ticket) or provide templates (ticket_template, template_gaps). The learning/caching purpose is unmistakable and differentiates it from the surrounding review-and-draft sibling set.

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?

Offers strong operational guidance: 'Call it once per project, not once per question' plus when to use from_tickets vs mining the tracker. However, it never explicitly compares against alternatives or states when-not-to-use — the differentiation from siblings is implied rather than stated.

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