search_files

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

With zero annotations, the description carries the full burden. It does disclose a real behavioral trait — a hard cap of 25 results — which is useful and not inferable from the schema. However, it says nothing about ordering, whether the cap truncates silently, whether output is paths plus summaries, or whether the call has side effects.

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?

Three short, front-loaded sentences with no filler; the scope and the exclusion come before the limit. The telegraphic style ("Max 25", with no noun for what is capped) costs it a point on clarity at the margin, but nothing is wasted.

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 read tool with no annotations and no output schema, the essentials (what is matched, what is excluded, result cap) are covered. What an actual result contains, how it is ordered, and how the 25-limit interacts with a broader match set are left unstated, leaving the agent guessing about return shape.

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 100%, so the schema already documents both parameters, and the description adds only that matching applies to path or summary (useful, since the schema just says "Text to match"). It says nothing about absolute_paths, but that parameter is already clearly described, so baseline 3 applies.

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 a specific operation on a specific resource: find files whose path or summary contains given text. It sharpens scope with a negative clause ("Not file contents"), which separates it from content grep, but it never mentions the actual siblings (find_symbol, query, who_imports/exports_in), so an agent must infer which file-oriented tool to pick.

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?

"Not file contents: grep for code" is an explicit when-not paired with an alternative, which is real routing guidance. It stops short of 5 because no sibling tool is named or contrasted, and no prerequisites or preconditions are stated.

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