get_files_touched

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

With no annotations, the description carries the full behavioral burden. It does disclose scope ('recorded sessions') and ordering, which is useful. It never states that this is a read-only, side-effect-free operation, nor whether results are paginated or bounded — gaps that matter more here because no annotations cover them.

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 sentences, no filler. The resource and its ordering come first and the usage cue follows, so the reader gets the essential facts immediately.

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?

The tool is simple and low-risk, and the description covers scope and ordering. However, with no output schema and no annotations, it should say at least roughly what a returned entry looks like and whether the list spans one session or all sessions, neither of which is resolvable from the structured fields.

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?

The tool takes zero parameters, so the schema has nothing to explain and the baseline of 4 applies. There is no argument syntax an agent could get wrong, and the description reasonably notes the scoping ('recorded sessions') that substitutes for a filter parameter.

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 resource and retrieval verb — every file the agent has touched — plus the ordering ('first-seen order'), which is real, non-obvious information. It does not, however, distinguish itself from potentially overlapping siblings like get_activity_summary or get_recent_events.

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?

'Use it to see the blast radius of the work so far before adding to it' gives a clear situational trigger, which is better than nothing. But it names no alternatives and sets no exclusions, so an agent weighing this against get_activity_summary or get_recent_events gets no help.

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