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

Annotations already declare non-readOnly, non-idempotent, open-world behaviour, so the bar is lower, and the description adds genuinely new context: text is ingested synchronously while a URL is crawled in the background over 'a minute or two'. That async distinction is the single most important operational fact here and it is not recoverable from the annotations. It stops short of saying what happens if the crawl fails or whether re-adding replaces existing knowledge.

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?

Two sentences with no waste, front-loading the purpose and then the behavioural difference between the two modes. The example payload types (prices, opening hours, policies) earn their place by clarifying what 'knowledge' means.

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 non-idempotent write tool with no output schema and full schema coverage, the description covers purpose, input modes and the sync/async timing that an agent must know before calling. It omits whether the call replaces or appends existing knowledge and what a successful background crawl returns, which would matter for a mutation 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 100%, so every parameter including url, text, title, agent_id and max_pages is already documented, which sets the baseline at 3. The description reinforces the url/text mutual exclusivity and the max_pages scoping, but adds no format, limit, or expectation beyond the schema's own text.

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?

A specific verb + resource: 'teach an agent' from a URL or from supplied text, which makes the two supported input modes immediately clear. It does not name or distinguish itself from the closer siblings (create_agent_from_website, create_agent_from_notes), leaving the agent to infer that this adds knowledge to an existing agent rather than creating one.

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 only implied: the description explains the two input forms and their timing, from which an agent can infer when to pick this over the create_* siblings. There is no explicit 'use when' statement, no exclusion of alternatives, and no stated prerequisite such as the agent already existing.

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