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

Annotations already declare non-read-only, non-idempotent, open-world behavior, and the description adds genuinely new traits: text is extracted and used for answering, failures are reported per document with a reason, and partial success still adds the rest. That partial-failure semantics is the key behavioral detail an agent needs and it is not derivable from annotations.

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 sentences, front-loaded with what the tool does before the per-document outcome and the plan requirement. Dense but every sentence adds an operational fact; no filler.

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 no output schema, the description usefully explains the return shape (per-document success/failure reporting) and covers prerequisites. Only minor gaps remain, such as size/count limits or default naming behavior, which are unlikely to block a correct call.

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 50%: the documents array shape ({url, name?}) is already documented in the schema, and the description only reinforces the URL-based input by listing formats. talk_id is undocumented in both places. Baseline 3 is appropriate since the schema carries most of the parameter burden.

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 (adds), resource (grounding documents for Q&A), transport (by URL), accepted formats, and target scope (an existing talk's private Q&A). It is clearly distinguishable from siblings like remove_qa_document, list_qa_documents and aitho_attach_script.

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 makes the use case clear (supplying grounding material to answer audience questions) and gives a real prerequisite: Presenter Pro, with the one-talk exception for free accounts. It stops short of naming a sibling alternative or an explicit when-not-to-use case, so it is strong context rather than full routing guidance.

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