Ranked search across projects

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond that: the ranking algorithm, that results are file:line ranges with snippets (important since there is no output schema), and the natural follow-up tools. It does not address index refresh or result staleness, which keeps it from 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?

Two tightly written sentences with zero filler. The core capability is front-loaded and the follow-up guidance is tacked on only after the essential purpose is stated.

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 search tool with no output schema, the description helpfully explains the return shape (file:line ranges with snippets) and the follow-up workflow, and annotations cover safety. The remaining gap is the undocumented refresh parameter and any index-freshness semantics, which an agent would have to guess.

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 60%: limit, matchAll and projects carry descriptions in the schema, while query and refresh have none. The description illustrates query semantics with a worked example but says nothing about refresh's behavior, and 60% coverage means the description does not fully compensate. 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 with real specificity: "Relevance-ranked full-text search (BM25 with fuzzy and prefix matching)" and what it finds ("passages about a topic"). It implicitly separates itself from the grep sibling via "ranked" and fuzzy/prefix matching, but never names grep, so the distinction has to be inferred.

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 example query and "finds passages about a topic" imply the right context, and it routes the agent onward to read_file/get_section for fetching text. However, it never states when NOT to use this (e.g. exact-match grep) or explicitly compare against the closest sibling, leaving the key choice to inference.

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