m365_files_search

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: it scopes the return payload to metadata rather than content, and discloses that result capping happens across internal pages, which is non-obvious server behavior. It stops short of describing match semantics or empty-result behavior, so not a 5.

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 sentences, zero waste, front-loaded with the capability and output scope, then alternatives, then the one non-obvious parameter caveat. Every sentence earns its place.

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 2-parameter read-only search with rich annotations and no output schema, the description covers capability, return shape, sibling routing and the top-cap behavior. Minor gap: nothing about match semantics (e.g. whether query is substring, prefix, or relevance-ranked) or behavior on zero matches, which could affect how an agent phrases the query.

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% and the schema already states that top is "Maximum total matches to return, not page size"; the description's closing sentence largely restates that. No added meaning for the query parameter (matching syntax, tokenization, scope) beyond the schema's example. Baseline 3 is appropriate.

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 ("Find matching items across your OneDrive") and bounds the output ("returning IDs, paths and basic metadata, not file content"), which immediately separates it from content-read and browse tools. An agent can distinguish it from the four m365_files_* siblings without opening any schema.

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?

Explicitly routes three alternatives: browse a known folder (m365_files_list), get item details (m365_files_info), read text content (m365_files_read). The condition selecting this tool (unknown location, name/keyword known) is implied by the contrast and is unambiguous in practice.

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