Local usage summary

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

No annotations exist, so the description carries the full burden and does well: it discloses that nothing is uploaded, that it only reads files the server wrote on save, and where those files live. It doesn't state cost, latency, or whether the report is cached, but the trust-relevant behavior is covered.

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, zero filler. The data source and the dimensions of the report are front-loaded, and the second sentence immediately answers the security question an agent would have.

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 does the work of explaining what comes back: counts of images and videos broken out by provider, format, and day. A sentence on the return shape (e.g. tabular vs. nested) would make it fully self-contained.

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% and the single optional since_days parameter is fully documented there. The description adds no syntax or meaning beyond the schema, which is the baseline case.

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?

Uses a specific verb+resource: totals the project's own .ai-media/manifest.jsonl and reports counts by provider, format, and day. That is far more precise than the title 'Local usage summary', though it doesn't explicitly contrast with neighbors like media_probe or media_cleanup.

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 scope ('this project's own manifest') implies when to reach for it, and 'this only reads' signals it's a reporting call. But there is no explicit when-to-use vs. when-not, nor a pointer to the sibling tools that answer related questions.

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