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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description still adds real value beyond them: a hard cap of 20 matches, the exact returned fields, the null-ref behavior for text-only hits, and the warning that results are untrusted page data — a genuine prompt-injection caveat an agent would not otherwise know.

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?

Three dense sentences with no filler: search semantics first, return shape second, safety caveat last. Every sentence carries information the agent needs and nothing is repeated from the schema or annotations.

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 usefully documents the return payload, count, and the 20-match cap, which is exactly the right compensation. It falls short on the input side, leaving two required, non-trivial identifiers unexplained for a tool that cannot be invoked without them.

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% across three required parameters. The description clarifies what `query` matches against and that matching is case-insensitive, but says nothing about `task_id` or `interaction_generation` — the latter is highly non-obvious and the agent is given no hint where its value comes from or why it must match the observation generation.

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 verb and resource: substring search over the latest delivered observation, naming exactly which fields are searched (labels, text, roles, safe attributes). It is clearly a search over already-observed data rather than a new observation, which separates it from task_observe in spirit, but no sibling is named explicitly.

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 clause "No browser access" implies this is a pure lookup against a snapshot and will not trigger a fresh observation, which is useful routing information. However, it never says when to prefer this over task_observe, task_extract or task_state, nor what precondition (a prior delivered observation) must hold.

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