recommend_tools

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered; the description adds genuinely new context by disclosing the ranking mechanism (lexical BM25 over name/description/tags), which tells an agent results are keyword-matched rather than semantically inferred. It does not mention ranking order or the limits of lexical matching, but the added context is substantial beyond the annotations.

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 short sentences with the action front-loaded and the mechanism as supporting detail; nothing is wasted or repeated.

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 explain return values, and annotations cover the safety profile; parameters are fully documented in the schema. The remaining gap is the absence of guidance on how this discovery tool relates to sibling routing tools, but for a two-parameter lookup this is nearly complete.

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 both parameters (query, top_k with default 5) are already documented in the schema. The description adds no format, length, or specificity guidance for the query beyond what the schema states, so the baseline 3 applies.

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 ('Recommend MCP-Dubai tools') plus the retrieval mechanism (BM25 over names, descriptions, tags), which is enough for an agent to know this is a meta-discovery tool rather than a domain lookup. It does not explicitly distinguish itself from sibling routing-style tools such as plan_query or list_features, which is the only thing keeping it off a 5.

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 'so the LLM can find the right tool without scanning the full catalogue' implies the situation to use it (unknown tool choice, large catalogue) but never states when not to use it or names an alternative like plan_query or list_features. Usage is inferable rather than prescribed.

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