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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description adds genuine extra context: matching is case-insensitive, scope is limited to text files (implying binaries are skipped), and results come back as 'path:line' plus the line text. It does not disclose result limits, truncation, or behavior on zero matches, which are the remaining behavioral unknowns.

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 short sentences, zero filler, with the scope and matching rule front-loaded before the return format. Nothing is repeated from the title or annotations.

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 simple two-parameter read tool with annotations and no output schema, the description covers purpose, matching semantics, file scope, and return shape. The gaps — query syntax, result caps, no-match behavior — are modest but real for a search tool.

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 only 50%: project_id is documented in the schema, but query is bare. The description partially compensates by noting the search is case-insensitive, but it never says whether query is a literal substring, a word, or a regex pattern, which is the key semantic question for a search parameter.

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 concrete verb and resource ('Finds text in every text file of a project') plus the matching rule (case-insensitive), so the operation is unambiguous. It does not name the closely-related siblings search_all_projects or find_references, so differentiation from them is left to inference.

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 phrase 'of a project' implies single-project scope, which weakly distinguishes it from a cross-project search, and 'every text file' implies a whole-project sweep rather than a targeted lookup. There is no explicit statement of when to prefer this over search, search_all_projects, or find_references, and no prerequisites beyond the required project_id.

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