search

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It identifies FTS5 as the engine and notes phrase treatment, but does not disclose return format (though output schema exists), ranking behavior, or limitations beyond operator unsupported. For a search tool, notably absent is any note about how results are scored/ordered or whether the search is subject to current workspace context.

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 a single concise sentence, and it's front-loaded with the key purpose. It's efficiently written with no wasted words, though it could add a small amount of usage context without harming conciseness.

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?

The tool is moderately complex with 3 paramters (1 required) and an output schema. The schema fully documents all parameters, and the output schema presumably covers return structure. However, with no annotations and a brief description, context around search semantics (ranking, scope across workspaces, how entity_type interacts with subtopic content) is thin, leaving residual ambiguity for agent selection.

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 100%, with clear descriptions for query (free text, phrase, no operators), limit (max results, default 20), and entity_type (optional filter with allowed values). Since the schema fully documents each parameter, the baseline of 3 is appropriate; the description adds no additional parameter semantics beyond what the schema already provides.

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 'Full-text search (SQLite FTS5) across all subtopic content' identifies the tool as a search over subtopic content using FTS5. It's reasonably specific about the mechanism (full-text search) and scope (all subtopic content), but it does not explicitly distinguish it from sibling search-like operations such as resolve_ref or list_* tools, and the description is somewhat brief about what constitutes 'subtopic content'.

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 implies the tool is for free-text searching of content across subtopics, and the query parameter note ('treated as a phrase, operators not supported') provides useful usage guidance. However, there are no explicit when-to-use or when-not-to-use instructions vs siblings like resolve_ref, get_context, or the list_* tools, leaving the agent to infer appropriate usage context.

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