Darwin-owned Public Sources

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description still adds real substance: static-only retrieval, allowlist restriction, bounded source/output limits, failure mode of no truncation, and auth context (free, no provider key). That failure and scope behavior is not derivable from the 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?

Front-loads the action and resource in sentence one, then stacks constraints efficiently. The trailing 'Free Darwin-owned hosting; no provider key required' is lower value but does answer an auth question, so it earns a partial place.

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?

Covers the full decision surface for a single-parameter fetch tool: what it will retrieve, what it refuses, what happens at limits, and what it returns. With an output schema present it need not spec return fields, and it still sketches them for orientation.

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 0%, so the description must carry the load, and it does add meaning the schema cannot express: the URL must resolve to an allowlisted official-source host and be publicly reachable and anonymous. It stops short of describing the URL's format nuances already enforced by the schema (https pattern, 2048 max).

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?

Names a specific verb (read) and precisely scoped resource (anonymous public HTTPS HTML/Markdown/plain-text document restricted to an official-source host allowlist). The enumerated non-JSON formats implicitly separate it from the read_official_json sibling, though the sibling is never named outright.

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?

Gives strong negative guidance: no JavaScript rendering, no search, no research conclusion, no login or paywall bypass, and fails rather than truncating. What is missing is an explicit positive route to the alternative (read_official_json) when the target is JSON.

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

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

Goes well past the readOnly/idempotent/openWorld annotations by disclosing that duplicate keys and invalid JSON cause failures, that no business data is inferred, and that the original decoded jsonText is returned with URL, retrieval time and SHA256. These are real behavioral traits an agent cannot derive from structured fields.

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?

Dense and front-loaded: the core action and host restriction come first, followed by return payload and failure modes. The closing sentence about free Darwin-owned hosting and no provider key is mildly tangential but still answers an auth question an agent might have.

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?

Covers constraints, failure behavior, and auth posture, which is more than enough given an output schema already describes the return shape. The one remaining gap is that the allowlist itself is never enumerated, so an agent cannot predict which hosts will be rejected.

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 0%, so the description must carry the semantics. It adds the key constraint the schema cannot express — the host must be on the explicit official-source allowlist — beyond the schema's bare '^https://' pattern. It does not mention the 2048-char max or min length, but those are visible in the schema itself.

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 a public HTTPS JSON document restricted to an official-source allowlist. The 'JSON document' framing distinguishes it implicitly from the sibling read_official_document, but the description never names that sibling or contrasts the two, so the differentiation is left to inference.

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?

Provides clear context plus hard exclusions: no credentials, no purchases, no auth/paywall bypass, no provider key needed. That tells an agent when this tool is appropriate. It stops short of naming the alternate sibling for non-JSON official documents or what to do when a host is not on the allowlist.

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