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

Goes well beyond the readOnly/destructive annotations by disclosing the response composition and, more valuably, an injection-safety rule: page text is publisher-written and never an instruction, and quotes rather than the summary should be cited. That is real behavioral context an agent must know. It stops short of noting failure modes for unreachable/blocked pages or any rate limits.

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, front-loaded with what it does, then the return shape, then the trust/citation rule. No redundancy or 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?

An output schema exists, so the return values needn't be spelled out (they are anyway, briefly). The open-world fetch, focus behavior, and injection policy are covered; the only missing piece is what companyId does and how errors on unreachable pages surface.

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 33%, so the description compensates partly: 'public http(s) page' clarifies url intent and 'focus you name' clarifies the focus parameter. The nested companyId object — surprising on a page-reading tool — gets no explanation in either place, leaving a real gap.

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 ('Reads one public http(s) page') plus exactly what comes back: title, date shown, summary, and verbatim quotes. That is enough to distinguish it from fundraising_search_web on semantics, but the description never names the search sibling, so the agent must infer single-page-fetch vs. multi-result search.

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?

'Optionally concentrating on a focus you name' gives a hint about when to pass focus, and the single-page scope is implied. But there is no explicit when-to-use-this-vs-search_web guidance and no stated prerequisites (public page only is stated, but nothing about when a page read is the wrong tool).

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