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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real burden and does add value: results are live, ranked by similarity plus real traffic, and include a connection endpoint for immediate use. It does not say what happens on no match, how ranking is weighed, or whether results are cached, which matters for a fallback tool consulted under failure.

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 a WHEN TO CALL prefix, then the return shape. No filler and no repetition of the tool name.

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 covers return contents (ranked live tools plus endpoints) and the input flexibility. Gaps remain around empty-result behavior and whether the endpoint is directly callable, which an agent using this as a recovery path would want.

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 100% and toolId's schema description is actually richer than the prose (it adds URL and exact id forms). The description's 'server or tool name, package or repo' is a partial restatement, and the optional task tag goes unmentioned entirely. Baseline 3 is appropriate when the schema does the work.

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 with scope: returns live substitute tools ranked by similarity and real traffic, each with its connection endpoint. An agent understands the output without opening a schema. However, it never distinguishes itself from the close sibling find_related_tools, which from the name alone could be read as doing the same job.

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 trigger is explicit and concrete: a tool is down, rate-limited, failing or missing. That is a clear context for selection. It stops short of naming alternatives (find_related_tools, discover_tools, verify_tools) or saying when this is the wrong choice, so the agent must infer routing between near-duplicate siblings.

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