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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds the 'load-bearing' epistemic claim and the limitation of cross-repo being future. However, it doesn't disclose how disagreements are detected or whether the result is exhaustive, leaving some ambiguity for a potentially nuanced operation.

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?

Only three sentences, front-loaded with the core purpose. The phrase 'highly load-bearing for honest epistemic surfacing' is promotional and adds little functional value. The example sentence is redundant and also incorrect because it omits the required `topic` parameter, but overall it is compact.

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?

With no output schema, the return description 'The detected points of corpus disagreement' is vague – it doesn't indicate shape, count, or limits. The repo limitation note is helpful, and the tool is relatively simple, but the description leaves gaps about what a result actually looks like and the exact semantics of 'disagreement'.

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 0%, so the description must compensate. It explains `repo` (restricts to intra-repo disagreement), but `topic` is only implied via 'on a topic'. The example 'call ... with arguments {}' contradicts the required `topic` field, making it misleading. Lacks detail on topic format or constraints.

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 clearly states the tool does 'Ask the corpus where its artifacts disagree on a topic' – a specific verb ('ask'), resource ('corpus'), and outcome ('points of disagreement'). It distinguishes itself from siblings like introspection_corpus_query by focusing specifically on detecting disagreement, not general querying.

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?

It explicitly explains the optional `repo` param restricts to intra-repo disagreement and notes cross-repo disagreement is a future tool, providing clear usage context. It doesn't name explicit alternative tools, but the intra/cross-repo distinction and the tool's specific purpose give enough guidance for when to use it.

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