search_tools

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that results carry cost tier and scope metadata, which is real context, but it omits important behavior: what an empty query returns (the only parameter defaults to ""), how many results come back, and whether matching is prefix, substring, or fuzzy.

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?

One sentence, front-loaded with the action and resource, with the return payload appended rather than buried. No filler.

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, return-value explanation is not needed, and annotations cover safety. What's missing is the operational context an agent needs: what "scope metadata" means for tool coverage, and the behavior of an empty query given the unlabeled default.

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 0% and the single parameter has no description, so the description carries the burden. It clarifies that matching is "by keyword" rather than exact or regex, but says nothing about the empty-string default — presumably listing everything — which is the most consequential semantic for this one 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 gives a specific verb+resource ("search available MCP screening tools") and names the matching dimension (keyword) plus the payload returned. It is clear what the tool does, though it never makes explicit that this is the catalog/meta-tool as opposed to the domain tools (run_tier1_screen, classify_screening_regime) that appear as siblings.

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?

There is no when-to-use or when-not-to-use guidance: nothing says to call this before invoking a screening tool, whether discovery is required or optional, or how it relates to the sibling domain tools. An agent must infer that this is the entry point for finding tools.

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