session_evidence

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

With no annotations provided, the description carries the full behavioral burden and handles it well. It explicitly states the operation is READ-ONLY, has no side effects, does not modify the session or browser, returns an error for nonexistent sessions, and notes that evidence persists after the session ends. It also discloses the append-only nature of the event log and the file types involved.

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 front-loaded with the most important signal ('READ-ONLY') and then provides a structured list of return fields. It is somewhat long but each section adds value: purpose, return shape, prerequisite, error behavior, and persistence details. No filler or repetition is present.

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 single-parameter read-only tool with no output schema and no annotations, the description is complete. It covers what the tool does, what it returns, the source of the required parameter, the error behavior, and what happens to evidence after the session ends. An agent has enough information to call it correctly and interpret its output.

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 0% for the single session_id parameter, but the description compensates by stating that session_id must come from a previous session_create call. It does not detail the exact format or type beyond what the schema already provides, but the provenance requirement is the most critical semantic information and is clearly conveyed.

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 'READ-ONLY: Retrieve the complete audit trail for a session', giving a specific verb and resource. It clearly distinguishes this from sibling session tools like session_pages or session_me by focusing on the full audit trail, and it states the operation is non-mutating.

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 gives explicit prerequisite context: the session_id must come from a previous session_create call, and it advises 'Use session_create first if you need a session.' It also notes the error case for a nonexistent session. It does not explicitly name alternative tools for when this should not be used, but the prerequisite and error behavior provide clear usage context.

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