knowledge_search

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It explicitly states 'Read-only', which is a critical safety trait, and explains the matching behavior (tokenization and AND logic), domain filtering, and limit enforcement. It could disclose more about response structure or error cases, but the core behavioral semantics are well covered.

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 two compact sentences with no filler. It leads with the core action, then packs in essential details about query semantics, domain, limit, and the alternative tool. Every sentence earns its place, making it a model of concise, well-structured documentation.

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 and no annotations, the description provides a strong baseline: it specifies query semantics, domain filtering, return limit, and read-only status, and points to the alternative for known IDs. It lacks explanation of app_id and the exact structure of returned atoms, but the core usage and constraints are clear enough for an agent to invoke correctly. This is above average but not fully complete.

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?

The schema has zero parameter descriptions, so the description must compensate. It explains 'domain' with examples, 'limit' by specifying it caps results, and 'query' by describing how tokens are matched. However, it leaves 'app_id' completely unexplained, which is a required parameter. This partial coverage justifies a middling score.

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 clearly states the tool's function: 'Search the fleet Postgres knowledge base by content'. It specifies the search semantics (whitespace-split, ALL tokens with AND logic) and distinguishes itself from the sibling kb_at tool by noting it fetches by ID. This makes the purpose unambiguous and uniquely identifiable.

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 gives clear context for when to use this tool: when searching by content rather than by known ID. It explicitly directs users to 'use kb_at to fetch a known atom by ID', providing a concrete alternative. It does not enumerate all other alternatives, but the key distinction from the most similar sibling is covered.

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