read

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

With no annotations, the description carries the full load and does well: it discloses the default content scope (main content only, no menus/footers), the effect of each flag, the 100000-character slice cap, and the non-obvious convention that the last line reports the slice end. It doesn't state prerequisites (e.g. that a page must be loaded/current) or how frames are handled, which keeps it off a 5.

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?

The core purpose is front-loaded in the first clause, and every subsequent sentence adds a distinct operational detail rather than repeating structured fields. It is dense but not padded; a slightly tighter pagination sentence would reach 5.

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 five-parameter, zero-coverage, annotation-free tool, the description supplies essentially everything needed to call it correctly, and the existing output schema removes the burden of describing return values. Minor omissions are preconditions (page must be loaded, frame context) rather than invocation mechanics.

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 description coverage is 0%, so the description must compensate — and it does for all five parameters: find, full, links, max_chars (including the 100000 ceiling) and start (as the continuation offset). Defaults are even echoed in prose ('by default links are plain text'), leaving no parameter ambiguous.

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?

It states a specific verb and resource — 'Return the current page's readable content as markdown' — and explicitly frames the scope as extraction/summarisation rather than interacting with elements. That contrast differentiates it from the action-oriented class of siblings (click, snapshot, type_text), though it never names a specific competing tool such as snapshot for the content-vs-structure decision.

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 gives concrete selection guidance: use find= for fast fact lookup, full=true for the whole page, links=true when URLs matter, and read(start=<end>) for continuation. The only gap is that it states no exclusions (when to prefer snapshot or network_requests instead), so an agent must infer the boundary.

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