measure_find_files

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

With no annotations, the description carries the full behavioral burden and largely meets it: it discloses the default search directories, that folder lookup is direct children with no recursion, the limit range, and the recognized file formats plus returned depth metadata. It does not explicitly confirm read-only/non-mutating status or mention any failure modes, leaving a small gap for an annotation-free tool.

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?

Purpose is front-loaded, followed by the usage scenario, parameter notes, formats, and return fields — a logical progression. It is dense but each line earns its place; the final return-value sentence slightly overlaps the existing output schema, and the paragraph flow is a touch unconventional, keeping it at 4 rather than 5.

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 two-parameter, zero-required discovery tool with an output schema, the description is fully sufficient: it covers what it finds, where it searches, how to use it when no path exists, parameter behavior, and recognized formats. An agent has everything needed to invoke it correctly.

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 0%, so the description must compensate — and it does fully. It explains folder semantics ('look only there, direct children, no recursion') with concrete defaults, and limit semantics ('1-100, default 20'), covering both parameters beyond what the bare schema provides.

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 verb and resource clearly: 'List recent measurable files on this computer, newest first, with what each contains.' An agent immediately knows this is a file-discovery tool. It does not, however, name or contrast itself against discovery-adjacent siblings like measure_open_capture or measure_depth_info, so it lands at 4 rather than 5.

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?

Provides an explicit, concrete usage scenario: when the user references 'this photo' or 'the scan I just took' with no file path, ask them to save to ~/measure-mcp-inbox or AirDrop to Downloads, then call this tool. This tells the agent both when to invoke it and what preparatory step to take, which is unusually actionable guidance.

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