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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description still adds genuine value by disclosing that matching is semantic ('search it by meaning') rather than keyword, and that results are ranked best-matching passages rather than whole articles. It stops short of mentioning ranking or threshold behavior, but the gap is modest.

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?

Sentences are front-loaded and mostly earn their place, with the disambiguation appearing early and the return shape stated plainly. The one inefficiency is that the exclusion of Spun's product documentation is stated twice, once in the opening parenthetical and again in the closing sentence.

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 annotations covering safety, a fully described schema and an output schema handling return structure, the description only needs to carry scope and sibling disambiguation, and it does both precisely. An agent has everything required to choose and call it correctly on the first attempt.

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%, so query, limit and tags are all documented in the input schema with types and bounds. The description adds no additional meaning about how the query is interpreted (natural language vs keywords) or how tags interact with the semantic search, so the baseline 3 applies.

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 names a specific verb (search) and resource (your organization's knowledge base), and immediately draws the boundary against sibling `search_knowledge` in a parenthetical. The enumerated subject matter (prices, policies, opening hours, procedures, product details) makes the content domain concrete rather than abstract.

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?

It states when to use it (organization's own information, anything its people wrote down) and when not to (questions about how Spun itself works), naming the exact alternative tool twice. No inference is required to route between the two overlapping search tools.

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