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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered; the description's "Does not change anything" is largely redundant with that. What it does add beyond annotations is genuine domain behavior: retired claims are kept because citing posts keep their wording and are never reactivated, active claims are the ones used by drafting and post checks, and a source with hasText=false cannot back a quote.

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?

Purpose is front-loaded in the first clause and the text is organized into purpose, data semantics, query behavior, and a Related footer. It is dense but nearly every sentence carries semantics; the only soft spot is the slightly tangled clause "query searches claim text, quotes and source titles, and source titles, links and text," which reads redundantly.

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 read-only listing tool with an output schema already present, this definition covers everything an agent needs: what is returned, what active/retired mean, how search behaves, and when to pass sourceId. Nothing required to call it correctly 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 all four parameters are already documented, establishing a baseline of 3. The description adds modest extra meaning, notably that query searches not only claim text and quotes but also source titles, links and text "like the page's search," and that sourceId additionally returns the source's full body — useful, but incremental over 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?

Opens with a specific verb and resource ("Lists the Claims & sources page") and immediately defines the two entity types: claims backed by a quote, and the sources they quote. It goes further than most list tools by explaining the domain model (active vs retired claims, source types, hasText) so an agent knows exactly what it is enumerating without opening a 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?

Gives concrete situational guidance: "Pass sourceId to see one source's full text (body) and only its claims, before quoting it in save_claim" ties this read tool to the downstream write tool, and the Related line names the mutation siblings (save_claim, retire_claim, add_source, update_source, delete_source). It does not state explicit exclusions or when another tool should be preferred, but no true alternative lister exists in the sibling set.

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