ToolRoute

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=true; the description does not contradict them and usefully explains the mechanism behind idempotency (same tools always yield the same set_id) plus retention (90 days after last use), cost (free), and the side-effect boundary for URLs. It doesn't disclose what happens if both or neither parameter is supplied, which is the one behavior an agent could trip on.

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?

Three tight sentences, front-loaded with the outcome (set_id for route_tools), followed by input modes and then behavioral guarantees. Nothing is filler or restated verbatim from the title.

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 correctly states the return value (a set_id) and its lifetime, and coverage of both params is effectively complete. The gap is the zero-required-parameter case: it never says what occurs if an agent supplies neither "tools" nor "url".

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 the schema already documents both parameters, including the max-500 cap and the 'listed, never called' URL semantics that the description repeats. The description's only added meaning is the deterministic set_id behavior, so this sits at the baseline-3 level rather than exceeding it.

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 (register) and resource (a tool list) and names the exact payoff: a set_id for route_tools. The sibling is called out by name, so an agent can distinguish register_tools from route_tools immediately.

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 clear selection logic between the two input modes: pass "tools" for inline definitions or "url" for a public remote MCP server, with the reassurance that URL-listed tools are never called. It implicitly frames this as the prerequisite step for route_tools, but never explicitly says when not to use it (e.g., if you already have a set_id) — that hint only appears inside the schema.

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

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

Annotations already declare readOnly/idempotent/closed-world, and the description goes well beyond them: BM25 keyword ranking with no LLM, adaptive shortlist sizing, confidence levels, token savings, output formats, and concrete rate-limit/pricing terms (200 calls/day per IP, $0.0005 via x402 or credits). That is exactly the operational context annotations cannot express.

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 core purpose and required inputs are front-loaded, and most of the density is genuinely useful (inputs, returns, ranking method). The trailing pricing/x402 sentence is secondary detail that dilutes the call-to-action slightly.

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?

There is no output schema, yet the description enumerates the return payload (shortlist, confidence, matched terms, token savings, injectable definitions) and the ranking method, which is everything needed to decide whether and how to call it.

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%, so the baseline is 3; the description earns a bump by clarifying the interplay the schema only hints at ('adaptive 3-12 tools, or "k"') and by explaining what set_id/tools mean in combination. It does not elaborate on max_k or the enum values in prose, so it is not a 5.

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?

Opens with a task-framed question ('Which of my tools does this task need?') and states the concrete action: send a query plus a tool set, get a ranked shortlist. It distinguishes itself from the only sibling by naming register_tools as the source of set_id.

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?

Explicitly tells the agent to supply 'set_id' (from register_tools) or 'tools' plus 'query', which is the key routing decision. It lacks an explicit when-not-to-use statement or failure-mode guidance (e.g., what to do on low confidence), so it stops short of a 5.

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