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

Beyond the annotations (readOnly/openWorld/idempotent/non-destructive), the description reveals a highly unusual behavior: the tool always returns an empty list with a specific `empty_reason: "upstream_removed"` value, and it deliberately fails rather than fabricating results. It even explains the historical cause (apiland.deno.dev shutdown on 2026-07-20). This is exactly the kind of trait annotations cannot convey. No contradiction with annotations exists.

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?

Every sentence earns its place: the NOT AVAILABLE status, the shutdown reason and date, the exact return behavior, the no-guessing policy, and the routing to alternatives. The critical operational facts are front-loaded ('returns an empty list with empty_reason') before the background detail. It is longer than typical descriptions, but the density of essential information justifies every word.

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 a simple 2-parameter tool with an output schema, the description is fully sufficient: an agent knows why the tool exists, what it will return in every case, what the empty_reason value will be, and which siblings to use instead. The only thing an agent might want (what a successful search would have returned) is impossible by design and covered by the output schema. Nothing needed for correct invocation or routing is missing.

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%, so the description must compensate; it partially does by contrasting 'know the module name' with free-text query search, which clarifies the meaning of the `query` parameter. The `limit` parameter is never mentioned, though its semantics are largely moot since the tool always returns an empty list regardless of input. The description adds meaningful context for the primary parameter but does not fully document either parameter.

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 says exactly what this tool does — it searches deno.land/x for modules — and immediately qualifies that the upstream API is gone, so it returns an empty list rather than results. It clearly distinguishes the tool from siblings by instructing that module or versions should be used when the module name is already known. This is a specific verb+resource definition with a crucial caveat, far beyond a tautology.

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 description explicitly states when NOT to use this tool ('If you know the module name, call module or versions instead') and names the exact alternative tools. It also explains the tool is a last-resort search that returns empty rather than guessing, which tells the agent this tool's search capability is effectively unavailable. No usage guidance is left to inference.

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