File Search

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals important operational traits: the filename search is case-insensitive and uses a bounded filesystem walk independent of the Windows Search index, while phrase search uses ADO with a PowerShell fallback. It also discloses the resultsTruncated flag, though it does not cover potential errors, permissions, or latency.

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 dense but every clause earns its place, covering search modes, backend mechanisms, constraints, and output flags. It is front-loaded with the core action and keeps technical details in parentheticals. It is slightly long due to implementation detail, but it is not redundant.

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?

Given there are no annotations and the output schema exists, the description sufficiently covers call requirements, parameter constraints, and return behavior via the resultsTruncated flag. It would benefit from explicit examples of filename/phrase formatting and a direct note about when to prefer this tool over sibling searches, but nothing critical is missing for 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 description coverage is 0%, so the description must compensate for the bare schema. It does this effectively by assigning semantics to all three parameters: filename as a substring, phrase as a full-text match, and scope as an absolute subtree. It also clarifies the mutual-exclusion-like constraint that at least one of filename/phrase must be provided and that scope is restricted to allowed roots.

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 states a precise operation: search files by a case-insensitive filename substring and/or a full-text phrase, optionally within an absolute scope subtree. It names the specific resource and mechanism, and clearly distinguishes itself from sibling search tools by focusing on files. Even without naming siblings, the scope and technical detail remove ambiguity.

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 description provides clear invocation constraints: at least one of filename/phrase is required and scope must be within an allowed root. However, it never explicitly states when to use this tool over alternatives such as file_get_info, mail_search, or onenote_search, nor does it describe when not to use it. Usage is implied by the resource type, not spelled out.

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