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

Goes well beyond the annotations: explains that each DNS/HTTP/redirect hop consumes a durable start before I/O, that the call is not idempotent and does not refund a lost response, that no JavaScript runs and completeness is not guaranteed, and that HTTP 200 can still carry a source/fetch failure. It also explains why readOnlyHint=false for an ostensibly 'read' tool. No contradictions with 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?

The scope and trial framing are front-loaded well, but the text is padded: 'No payment or settlement receipt' is stated twice, and the enumeration of readMarkdown JSON fields (ok, sourceOk, status, error, markdown, truncated, capture) duplicates the existing output schema. Several sentences could be merged without losing meaning.

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 two-parameter network fetch with high-impact billing semantics, the description covers cost accounting, idempotency, failure modes, content fidelity limits (tables, no JS), and truncation behavior. With an output schema and full annotation coverage already present, nothing an agent needs in order to call this safely is missing.

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 100%, so both parameters are already documented with bounds and defaults. The description restates the markdownLimitChars range (1-40000, default 40000) without adding new semantics, and says nothing extra about the url parameter beyond what the schema's 'Private, loopback, and non-public hosts are refused' already covers. Baseline 3 applies.

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 ('Read one public HTTP(S) page as bounded Markdown') plus the access mode ('walletless trial'). It explicitly separates itself from the paid sibling read tool and from extract ('Read and extract share the same original authority, remaining hops, expiry...'), so an agent can route correctly without opening any schema.

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?

Clear usage context: this is the walletless, allowance-consuming trial path, with the paid alternative spelled out ('The paid next path stays GET /read?url={encodedPublicUrl}'). It also warns that retries spend another hop, which is effectively a when-not-to-retry guideline. It stops short of an explicit 'use this when you have no wallet/settlement credits' statement, leaving the selection condition lightly implied.

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