session_log

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

No annotations are present, so the description carries the transparency burden. It discloses ordering, per-line fields, and filtering behavior, and the 'git log' analogy implies a read-only operation. It does not explicitly state the side-effect profile, but nothing about the description suggests mutation.

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?

Two dense sentences front-load the return format and then add usage guidance. There is no filler, repetition of schema details, or vague phrasing.

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 simple optional-parameter log reader with no output schema, the description supplies the necessary return fields, ordering, and a decision rule for filtering. It is complete enough for an agent to invoke it correctly without further context.

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 100%, with clear descriptions for limit, session_id, and type_filter. The description only reinforces 'Filter by type', adding little beyond what the schema already says. Baseline 3 is appropriate when the schema carries the parameter documentation.

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 names the exact resource ('sessions'), the operation mode ('git log'), and the output shape (one line per event, newest first, timestamp, event type, repo state). It is immediately distinguishable from write/status/search siblings by its read-only log framing, even though it does not explicitly name an alternative tool.

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 concrete directives: 'Use it to scan history fast, then grep the session's own session.md' and 'Filter by type to answer what has already failed here'. This establishes a clear primary use case and points to a follow-up resource, but it does not explicitly say when to prefer session_search instead.

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