search

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

Annotations already declare readOnlyHint, idempotentHint and closed-world behavior, so the safety profile is covered. The description goes beyond them by disclosing the matching mechanism (word and word-ending matching, plus meaning-based matching that only works when a local model is installed) and by pointing to the reply's mode field as the ground truth for which path ran.

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 sentences, no padding, and the content-type scope is front-loaded before the matching mechanics. It is efficient, though the second sentence is a fairly dense clause stack.

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?

With six parameters, 33% schema coverage and no output schema, the description is only moderately complete. It covers search semantics and the semantic-mode prerequisite, but leaves parameter behavior (limit, project_id, mode values) and the shape/ordering of returned results to inference.

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 33% (only project and content_types carry descriptions), so the description needs to compensate. It partially does by explaining keyword vs. meaning matching, which is what the undocumented mode enum controls, but it never names the mode parameter or its auto/keyword/meaning values, and limit, query and project_id remain unexplained in both places.

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 gives a clear verb (Search) plus the exact resource universe (todos, decisions, changes, learnings, problems, solutions), so an agent can tell it is a cross-type finder rather than a writer. It does not, however, contrast itself with sibling retrieval tools such as get_learnings, get_recent_changes, or history, and the tool name alone ('search') is generic.

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?

Usage is only implied: enumerating the six content types hints that this is the tool to reach for when you want to look across categories. There is no explicit when-to-use, no when-not-to-use, and no named alternative (e.g., 'prefer get_learnings for a known content type'), even though many siblings compete for the same intent.

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