Inspect or maintain the local index

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but they are tool-level and cannot say that the danger is confined to specific actions. The description adds per-action detail by naming `stats` as safe and `clear`/`prune` as permanently deleting data, which is genuinely useful disambiguation. It doesn't cover what `vacuum` does or what stats returns, so it stops short of a 5.

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?

Two sentences, front-loaded with the capability and immediately followed by the safety-relevant distinction. Every clause earns its place and nothing is padded.

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 an action-dispatch maintenance tool with 5 optional params and no output schema, the description covers purpose and the primary risk (permanent deletion). It could say more about what `stats` reports or how `vacuum` differs, but with 100% schema coverage and destructive annotations, the essentials are present.

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%, and the schema fully documents scope, action, format, max_pages, and max_age_days. The description only echoes the action names already enumerated in the schema, adding no syntax, defaults, or interaction detail beyond it, so the baseline 3 applies.

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 pairs concrete verbs (report, prune, clear, compact) with a specific resource: the local cache of fetched pages and recent engine responses. This is far more than a restatement of the name, though it never names or differentiates itself from siblings like search_index or list_engines.

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 line '`stats` is safe and cheap; `clear` and `prune` delete data permanently' hints at action selection, but there is no explicit 'use this when' guidance and no comparison to the sibling index/engine tools. The agent must infer that destructive maintenance is only warranted in specific situations.

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