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

Adds real behavioral context beyond the annotations: idempotent replay by request identity, a hard cap of ten verified excerpts, signed result ids and reference URLs, and an authentication plus active paid-plan prerequisite. It also states 'cannot change files,' which is consistent with destructiveHint=false; the readOnlyHint=false annotation is not contradicted, since billing/metering side effects are plausible, but the description never explains that non-read-only aspect.

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 opening sentence about retrying 'the same public search with the same MCP request identity' is dense and refers to 'public search' in a way that sits awkwardly with the private/licensed catalogs mentioned later. The fragment 'Paid context routing for useful work.' is pure marketing and earns no place, while the genuinely useful limits and prerequisites are buried mid-paragraph.

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 an output schema present, the description needn't specify return structure, and it nonetheless sketches result shape (ten verified excerpts, coordinates, signed ids, URLs). Combined with auth/plan requirements, idempotency semantics, and corpus-coverage caveats, an agent has enough to call it correctly; only the missing sibling routing and the unexplained non-read-only side effects keep it from a 5.

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?

Only one parameter exists and schema description coverage is 100%, so the schema already defines the query field, its 1–4096 length bounds, and the eligible catalog types. The description's phrasing ('route a question across policy-eligible Tier 1 context, including private, shared, licensed, or public catalogs') largely restates the schema text rather than adding format, phrasing, or scoping guidance.

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: 'Route a question across policy-eligible Tier 1 context available to the account,' and enumerates the catalog types it can span (private, shared, licensed, public). The scope is clear, but it never names the sibling tools (fetch, render_context_results, authorize_sources) to differentiate itself, and the 'Tier 1 context' framing is internal jargon that requires the surrounding sentences to decode.

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?

Gives useful boundaries: 'Broad questions may need focused follow-up searches,' 'absence from one result set does not establish absence from the corpus,' and 'This is not an unrestricted web crawler.' These imply when to use and when to escalate, but there is no explicit routing to the siblings (e.g., when to prefer fetch or render_context_results), so an agent must infer the division of labor.

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