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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely useful result information (relevance ranking, verification state, version validity) that no output schema provides, but it says nothing about match semantics (substring vs. token), ranking details, pagination, or rate limits.

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 core purpose is stated in the first sentence, and the return-value summary is second. The trailing attribution line ('Served by BufferOverride...') is boilerplate that does not help an agent invoke the tool, but the overall text is tight and front-loaded.

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?

This is a simple two-parameter read tool with full annotation coverage, so the bar is modest. Still, the lack of any mention of the limit parameter's role or result pagination leaves a real gap for an agent expecting more than the default 10 matches.

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 only 50%: the query parameter is documented as 'Error text or keywords,' but the limit parameter has no description beyond its default of 10 and maximum of 50. The description does not mention limit, paging behavior, or what happens when more results exist than the limit, so it does not compensate for the coverage gap.

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 definition uses a specific verb-plus-resource phrase ('Full-text search over public questions') and states what results look like. That is enough to distinguish it from bufferoverride_list_questions and bufferoverride_get_question, but it never names those siblings or explains why an agent would choose full-text search instead of listing.

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?

The only usage hint is 'Error text or keywords to search for' in the schema, which implies that the tool is for keyword and error-text lookups. The description offers no explicit when-to-use, when-not-to-use, or alternative-tool guidance, so an agent must infer the context.

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