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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description adds genuinely useful non-obvious behavior: answers are grounded in exact quotes, long documents are pre-searched with embeddings, and each call costs $0.02 USDC via x402. The cost disclosure is valuable context an agent cannot get from structured fields, though return format and limits remain unspecified.

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 compact sentences with the core purpose front-loaded and no wasted filler; inputs, output characteristic, and cost are each covered once. The construction is dense and efficient, with only minor awkwardness in the opening phrase.

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 3-parameter Q&A tool with no output schema, the description covers the essentials: accepted input formats, the quote-backed nature of the answer, the embedding search step, and the per-call cost. Adding whether url/text are exclusive and what happens on retrieval failure would make it 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?

Schema coverage is 67% and the schema descriptions are terse ('Document or page URL', 'Raw text instead of url'). The description meaningfully extends this by enumerating accepted document types (web page, PDF, Word, Excel, CSV) and clarifying that raw text substitutes for a URL. It stops short of stating whether url and text are mutually exclusive.

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+resource ('ask a document') and a concrete result ('get an answer backed by exact quotes'), making the document-Q&A function unambiguous. However, it never differentiates itself from close siblings like docs_ask, answer, or cite, which an agent must choose between.

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 implied by the input shape (provide a URL or raw text plus a question), but there is no explicit when-to-use guidance, no exclusions, and no reference to the sibling tools that also answer questions over content. An agent must infer the selection criteria on its own.

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