Search Project Files

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

The description adds substantial behavior beyond the annotations: the text-only content limitation for binaries, the recursive default trap (top-level only; '**' alone does not descend), client-side pagination with the server returning the full match set, scope semantics for SUBTREE vs ANCESTORS, version targeting, and branch pinning behavior. None of this appears in the annotations, yet all of it shapes call results. The readOnlyHint=true annotation is fully consistent with the described search semantics.

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?

The description is long (~200 words) but every section earns its place given 14 parameters and multiple non-obvious traps; critical warnings are front-loaded in CAPS and the core function leads the first sentence. It loses a point because it partially restates schema content — extensions, scope, recursive, and branch each already have parameter descriptions in the schema — making it denser than strictly necessary.

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?

Despite having no output schema, the description discloses the return shape ('path, name, type, size'), pagination behavior, endpoint mapping, scope/version/branch semantics, the binary content limitation, and recursion defaults. For a 14-parameter tool with three enums and a high trap surface, there is no meaningful missing context an agent would need before invoking 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 coverage is high (86%), so the schema already documents most parameters; the description goes beyond it on the foot-gun parameters: recursive's '**' trap, content's text-only restriction, and pattern's binary caveat with the '**/' vs '*.xlsx' distinction. The description adds real nuance that the schema alone does not convey, though the schema still carries the primary weight for the majority of parameters, so a 4 is appropriate rather than a 5.

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 first sentence names the exact verb, resource, and the four search dimensions ('ant-glob path pattern', 'extensions', 'type' FILE/FOLDER/ANY, case-insensitive 'content' substring). It maps to a concrete endpoint and ends with two realistic query examples that leave no doubt about what the tool does. The scope ('search a project's files and folders') clearly distinguishes it from siblings like openl_read_project_file, which reads a known file, and openl_list_projects, which lists projects.

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?

Explicit when-to-use guidance is given with concrete questions ('where is portability loading mentioned in XML or Markdown?') and the exact parameter recipe to answer them (content, recursive=true; pattern '**/*.xlsx', recursive=true, without content). It also states when NOT to use content search — binary files must be 'read/download them separately' — and warns that combining content with a binary pattern yields no matches. This is full when/when-not coverage.

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