session_report

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

With no annotations, the description fully discloses behavior: generates HTML and PDF, includes screenshots, redacts secrets, resets journal with clear, and notes appear at top. It also mentions that the journal records automatically from server start. No contradictions.

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?

The description is a single paragraph of about 4 sentences, front-loaded with purpose. It is concise and includes necessary details without redundancy. Could benefit from slight structuring, but overall effective.

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 complex tool with 5 parameters and no output schema, the description explains the output format (HTML+PDF) and content (verdicts, timings, errors, screenshots). It also covers the clearing mechanism. It is complete enough for an agent to understand the tool's behavior and expectations.

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%, and the description adds significant meaning beyond the schema: explains overall purpose, that notes appear top, that clear resets journal, and that screenshots are embedded thumbnails. The schema descriptions are already clear, but the description integrates them into the tool's context.

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 clearly states the tool generates a human-readable dossier of everything done in the server run, including tool calls, arguments redacted, verdicts, timings, errors, and screenshot thumbnails. It distinguishes itself from siblings like get_report by specifying it covers all calls and produces HTML+PDF.

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 description explicitly says it is for handing to the user to review the whole session and suggests adding findings via notes. It also explains the clear=true usage 'between test rounds'. However, it does not explicitly state when not to use it vs alternatives like get_report, but the context makes it clear.

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