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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered by structured data. The description still earns credit for adding behavioral detail beyond those fields: the authorization requirement ('public or user-authorized'), and the explicit guarantee that nothing is captured or persisted, which is the kind of side-effect disclosure annotations do not express. It does not discuss failure modes on unreachable or blocked URLs, so it is not 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?

Two sentences, both front-loaded with the operative information: the first states what is fetched and what is inspected, the second immediately rules out screenshots and persistence. No filler, no repetition of the title, and the negative constraint is placed where a reader will see it before deciding to call.

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 description is not obligated to explain return values, and the annotations cover the safety profile. Combined with full schema coverage on two parameters, what remains is only the missing routing guidance against the five sibling tools in this reproduction pipeline. That is a real gap but the only one of substance.

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% and both parameters are documented inline, including the 1-30 second timeout range, so the schema carries the parameter burden. The description adds nothing about the timeout's default behavior or what happens when it elapses. A baseline 3 is correct when the schema already does this much work.

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?

The description uses a specific verb ('Fetch') plus a concrete inventory of what is inspected: title, metadata, frame policy, and source/embed candidates. That is far more than a restatement of the name. It stops short of 5 because it never names or distinguishes itself from the closely related siblings discover_embed_candidates and generate_embed_snippet, so the boundary of 'likely source/embed candidates' versus 'discover_embed_candidates' is left ambiguous.

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 implied by the phrasing ('public or user-authorized URL') and bounded negatively by 'Does not capture screenshots or persist artifacts', which tells an agent one thing this tool is not for. However, there is no explicit when-to-use statement and no reference to any sibling tool, so an agent must infer whether to call this before plan_reproduction_path or instead of discover_embed_candidates.

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