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

Annotations already declare the mutation profile (readOnly=false, destructive=false, non-idempotent, openWorld), and the description adds real context beyond them: no credit spend, and url/sitemap content is crawled asynchronously rather than processed inline. The async background behavior is the key trait an agent needs and is disclosed. A minor gap remains: duplicate or re-submission behavior is not explained despite idempotentHint=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?

Four short sentences, front-loaded with the credit-cost reassurance and the behavioral distinction between pasted and crawled content, then the polling instruction. Every sentence carries actionable information; nothing is padding.

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 mutation tool with no output schema and partial parameter coverage, this gives the agent the essentials: cost, sync vs async processing, and how to detect completion. The only meaningful omission is what a successful call returns (an id? a job handle?) and how to handle repeat submissions.

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 only 50%, so the description must carry weight. It does: it enumerates the four content_type values and maps each to how content arrives (text/article pasted in vs url/sitemap crawled), which covers the conditional-requirement logic that the schema only partially documents. Title remains unexplained and the article_id-to-content_type linkage is the schema's job.

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?

"Add knowledge to a chatbot" is a specific verb+resource pairing that clearly separates it from ask_chatbot (querying) and chatbot_status (checking progress). It does not explicitly name a sibling, so it stops just short of 5.

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 each content_type applies and prescribes the follow-up workflow ("Poll chatbot_status until training is complete"), which gives the agent a clear operational sequence. It does not name an alternative tool to use when adding content is the wrong choice, so there is no explicit exclusion.

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