get_web_source

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

Annotations only cover the safety profile (readOnly, openWorld, non-destructive), while the description adds substantial behavior: returns author/date/licence/snapshots, an earliest-snapshot date fallback for undated pages, HTML+PDF support, sectioned returns for long pages, stopping at bot checks, and refusing local addresses. That is far beyond what the structured metadata conveys.

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-loaded with purpose, then usage, then edge-case behaviors in short declarative sentences. Slightly dense and long, but every sentence carries distinct information about the return payload or edge cases rather than 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?

There is no output schema, so the description must carry the return burden, and it does: text plus author, date, licence, snapshots, sectioned long pages. It also documents the key failure modes (bot checks, local addresses) needed to call it correctly.

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 the baseline is 3. The description reinforces the 'section' semantics ('Long pages come back by section'), matching the schema's note that it comes from an earlier call's outline, but adds no new syntax or constraints beyond the schema.

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 (Read) and resource (public web page), then concretizes it with examples (blog post, newsletter, club or vendor article). An agent knows exactly what comes back: page text plus author, date, licence and Wayback snapshots. No sibling tool overlaps this scope, so differentiation is implicit.

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 a clear when-to-use rule: 'for methods first published on the web ... after finding the page with a web search,' which also sequences it after a search step. It does not state explicit exclusions or name an alternative tool, but none of the paper/provider siblings competes for this job.

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