get_report

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

Adds substantial context beyond readOnlyHint: it discloses the privacy guarantee ("No file paths from the machine are included"), clarifies what verification actually proves ("the cited place exists, not that the claim is true"), and honestly flags the one side effect ("apart from creating the workspace if it doesn't exist"). The last point is exactly the kind of nuance annotations cannot convey.

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-loads the resource and its contents before the format/verify details, and every clause carries information. The single dense paragraph with nested parentheticals is harder to scan than a short bulleted structure would be, which keeps it off a 5.

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 still describes the return shape well (claims, status, confidence, reasoning, evidence provenance, graph entity) and the three serialization formats. Combined with the disclosed side effect and verification semantics, an agent has everything needed to call this correctly.

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%, so the baseline is 3, but the description adds real meaning: it explains the purpose of each format value and spells out the semantics of verify ("a fresh check that the cited file and line exist") and of the workspace side effect. The status filter is only covered by the schema, not the prose.

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 and resource ("Produce a report of a workspace's findings") and immediately enumerates the report's contents: claims with status/confidence/reasoning plus evidence provenance. This clearly separates it from sibling list_findings, which returns raw entries rather than an assembled, format-selectable report.

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 concrete usage context for the format choice — markdown "for reading", json "for tools", sarif "for code-scanning viewers" — and explains when to set verify=false ("a faster report that skips the file checks"). It never names an alternative tool (e.g. list_findings) or states when not to use it, so it falls short of a 5.

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