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

Annotations already declare readOnlyHint and openWorldHint=false. The description adds genuinely useful context beyond that: a scope cap ('At most 12 sites are read'), the return grouping ('bySite', 'quoted'), and a semantic caveat ('similar in meaning, not right, and not cited by an assistant'). It doesn't cover result ordering edge cases but adds real value.

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?

The content mostly earns its place, but the single run-on sentence is hard to parse ('and each site once by its best passage under "bySite", from the sites closest...'). Return shape and filtering options are tangled together rather than front-loaded, hurting readability.

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 description earns credit for sketching the return shape ('bySite', 'quoted') and the 12-site scope. However, it omits limit behavior, empty-result handling, and ordering, leaving meaningful gaps for a search tool whose return contract isn't otherwise documented.

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 100%, so both 'sites' and 'market' are documented in the schema. The description echoes the market/site filtering ideas but adds no format or behavioral detail beyond the schema, matching the baseline-3 case where structured fields do the heavy lifting.

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 action (ask a question, get answering passages) and the resource (passages grouped under 'bySite' and 'quoted'). It's clear this is semantic retrieval, but it never names or contrasts a sibling (e.g., mttr_similar, mttr_explore), so an agent must infer differentiation on its own.

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?

Filtering options ('from the sites closest to the question, one market, or named sites') imply when to use it, and the 'similar in meaning, not right' caveat frames expectations. But there is no explicit when-to-use/when-not or named alternative, so guidance is only implied.

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