consult_human_agent

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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false, and nothing in the description contradicts them. The description adds useful behavior beyond the annotations: session continuity via session_id, the deep-homework trigger semantics, and the cited-insights/next_moves return shape. It omits any auth, cost, or latency characteristics for a tool that spawns human work.

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?

Front-loaded with the triggering condition, which is good, but the middle sentences lean on marketing abstraction ('practitioner depth, proprietary frameworks', 'verified real-world expertise and published thinking') that adds little selectable signal for an agent. The useful operative facts (deep mode, return shape) are buried at the end.

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 does discharge the return-value burden by naming 'cited insights and next_moves', and all six parameters are schema-documented. The one real hole is sibling differentiation from consult_analyst, which the description never addresses despite that being the primary invocation risk.

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%, so every one of the six parameters is already documented in the schema, including 'deep', 'session_id', and the analyst_id routing/never-expose-raw-IDs rule. The description only restates 'Supports deep homework mode (deep: true)' and adds no syntax, defaults, or edge-case meaning beyond the schema, 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+resource ('consulting an ... Human Agent') and enumerates the value it produces (practitioner depth, proprietary frameworks, strategic guidance; cited insights and next_moves). It never names or distinguishes itself from the obvious sibling consult_analyst, so an agent must infer the split from the name alone.

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 opening 'Use when consulting an authorized living Human Agent' plus the 'On-Request Human Agents undergoing onboarding' clause gives a partial when-to-use condition. However, there is no explicit when-not guidance and no mention of the near-identical 'consult_analyst' sibling or 'find_expert'/'list_analysts' as the upstream discovery path (those appear only inside a parameter description).

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