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

With no annotations, the description carries the full burden and does meaningful work: scoring is deterministic (no LLM), raw responses accumulate and can be retaken, and the human's observed profile stays unpublished until approved. These are non-obvious behavioral facts not derivable from schema.

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?

Dense but front-loaded: the source distinction and evidence rule come first, publishing caveat last. Every sentence carries load, though em-dashes and parentheticals make it slightly hard to scan.

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 3-param mutation tool with no output schema or annotations, the description covers the essential semantics: what each source means, the answer vocabulary, evidence discipline, retake behavior, and the publish gate. Only the auth token mechanics are left to the schema.

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 low (33%), so the description must compensate, and it does: it maps the source enum to distinct answer vocabularies — agent_deep uses exactly agree/disagree/unobserved while likert values apply to human_short. This meaningfully constrains the answer enum beyond the schema. The agent_token param is only described in the schema.

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: 'Submit a Pair Profile take (registered pairs).' An agent can tell this is the profile-response submission tool vs siblings like pairgora_profile_questions or pairgora_profile_publish, though sibling differentiation is implicit rather than explicit.

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?

Clearly specifies when to use each source: 'source agent_deep = you, answering the deep binary form from your logs' and that likert values belong to human_short. Gives the evidence discipline rule (answer only from actual logs, else 'unobserved') and notes retaking as logs grow. No explicit exclusions but context is strong.

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