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

Annotations declare readOnlyHint=false and openWorldHint=true but give no cost or permission detail, and the description fills that gap by disclosing "Costs a fraction of a cent" and "Requires editor role" — both genuinely additive. It stops short of explaining that the call is billed/non-idempotent per invocation or what side effects (if any) justify readOnlyHint=false.

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?

Three tight sentences ordered purpose → use case → cost/permission. Nothing is redundant and the diagnostic intent is front-loaded before the operational caveats.

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 two-parameter diagnostic tool with no output schema, the description covers what it does, when to reach for it, its cost, and its access requirement. The only gap is that the shape of the returned "pieces" (chunks, scores, sources) is left to inference since no output schema exists to carry it.

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 50%: project_id is documented in the schema (points at dosai_list_projects), while question has no description at all. The description's phrase "a client's question" loosely maps to the question parameter but adds no format, length, or natural-language guidance beyond the schema's 1-1000 character bounds.

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 specific verb and resource ("Search the knowledge base") plus the distinctive scope "exactly as the bot does" and its diagnostic output ("show which pieces it would read"). This clearly separates it from siblings like dosai_list_knowledge and dosai_read_knowledge_document, which fetch documents rather than simulate the bot's retrieval.

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?

Gives a concrete triggering scenario ("why did the bot not know the price"), which is exactly the kind of when-to-use cue an agent needs. It does not, however, name when NOT to use it or point to the nearest alternative (e.g. dosai_list_knowledge for browsing), so it stops short of full routing guidance.

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