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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial non-obvious behavior: top-3 get one live MCP handshake, a probe proves only one answered call, ERC-8004 registration proves a claim not function, null feedback ranks below zero, and no job-outcome data exists. It also discloses a real coverage gap (keyless ERC-8004 enumeration is not callable). This is exactly the extra context annotations cannot supply.

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?

Labeled sections (USE WHEN, RULE ENFORCED, COVERAGE, Returns, Example) front-load the essential routing decision and are dense with signal. Some sentences restate the same caveat twice (declared vs. working service) and the whole block is long, so it is efficient but not maximally tight.

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 no-output-schema tool, the description spells out the return shape including the unknown branch, candidates_considered, probed and coverage, and states the semantic caveats an agent needs to interpret the result. Nothing needed to call or interpret the tool 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 100% and the schema fields are already annotated with nuance (chain filters the passport pool, requires_mcp means declared-only). The description adds only a single example call, so it does not meaningfully extend parameter meaning beyond the schema. Baseline 3 is appropriate.

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 ('Choose an agent for a task, with the pick explained') plus the signal basis of the choice (registration, service, feedback, liveness). An agent can identify this as the routing/pick tool. It never names the nearest siblings (search_agents, recommend_stack, route_swap) to draw the boundary explicitly, so it falls short of 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?

'USE WHEN an agent needs another agent for a task and wants the pick explained' gives clear triggering context, and it states the fallback rule ('when nothing qualifies the answer is unknown ... never a low-confidence pick'). No explicit when-not or named alternative tool is given, so 4 rather than 5.

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