report_bug

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

With no annotations supplied, the description carries the full burden and does so well: it discloses exactly what data is collected (version, OS, jurisdiction, tool, error message), that search text and ids are stripped, that the user sees a confirmation dialog, and that no transmission happens without approval. This is the kind of privacy and side-effect context an agent cannot infer from structured fields.

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?

Purpose and the usage gate are front-loaded, followed by the data-collection facts and then the parameter guidance in a clean Args block. The clause "decides whether to send it; nothing is sent otherwise" is mildly redundant but reinforces the no-side-effect guarantee, so it earns most of its space.

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?

The tool is simple (one optional string) and an output schema exists, so return values need not be explained. The description still covers trigger, collected fields, redaction, user confirmation, and parameter constraints – everything an agent needs to call it correctly and safely.

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 description coverage is 0%, so the description must compensate for the single 'note' parameter, and it does: it defines the parameter as the user's own words for what went wrong and adds an explicit constraint against pasting document text, search terms, or client details unless the user asks. That constraint meaningfully changes how an agent should populate the field.

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 specific verb and resource: "Prepare a bug report about Fontes for its developers." It also scopes the artifact (version, OS, last failed call details), which no sibling tool in the catalog does, so an agent can distinguish it from search_caselaw or get_decision without a schema lookup.

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?

It gives an explicit trigger condition – "Only when the user asks to report a problem" – plus a strong negative guarantee that nothing is sent otherwise. An agent knows both when to call it and when not to, which is the whole decision surface for a one-shot reporting tool.

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