Build a session report

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

Annotations declare readOnlyHint=false and non-idempotent, and the description adds real behavioral context beyond that: which URI is meant for reading (reportMdUri), that reportUri is the full JSON and is returned inline only with format:"json" and without steps, that reportHtmlPath is a path to hand to the user, and that playwright is deprecated. Error cases and write side effects (does it persist files, where) remain undisclosed.

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?

Front-loaded with the action and its outputs, then formats, then a CI pointer — no filler sentences. The parenthetical "inline with format:"json" minus steps" is densely compressed and takes a re-read to parse.

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 no output schema, the description carries the return-value burden and does so by mapping each URI to its purpose, which is the key information for a report builder. It is slightly thin on prerequisites (must a session be started first) and on error behavior for an invalid sessionId or format/existing baseline.

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 only 50% (format and sessionId lack descriptions), but the description compensates by explaining format's export semantics, its interaction with reportUri, and the deprecated enum value. baseline and trendRoot are already documented in the schema, so the description does not need to repeat them.

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 concrete verb+resource ("Build the session report") and immediately enumerates the three artifacts it returns, so the agent knows exactly what comes back. It does not explicitly differentiate itself from adjacent tools such as qa_get_artifact, keeping it short of a 5.

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 clarifies that format "adds an export" (i.e., the default summary is enough unless an export is needed) and points to docs/ci-reports.md for CI usage, which implies when the export formats matter. There is no explicit when-not or named alternative for retrieving existing artifacts, so guidance 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.