prepare_relationship_observation_note

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

Goes well past the readOnly/idempotent annotations: it discloses that only the source anchor is recomputed, that the statement is not verified and answers are not inferred, and that nothing is persisted or changes calculation facts/counts. The 'Never invent client reports' guardrail is exactly the kind of behavioral constraint an agent cannot get from structured fields.

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-loads what is produced and where it goes, then prerequisites, then exclusions. The exclusion list is long but each clause carries real constraint; a slightly tightened phrasing would remove some density without loss.

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?

Covers prerequisites, optional links, and behavioral limits well for a 6-parameter tool, and annotations plus hints cover the safety profile. However, with no output schema and no statement of what the returned note/anchor looks like, an agent cannot predict the response shape or how to pass it on.

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?

With 0% schema coverage, the description does heavy lifting: it explains reference must be an unchanged calculation reference, person is a/b, statement must be explicitly supplied and human, and point/question_id are optional links. It never mentions author_role or its client_report/practitioner_note distinction, which is the one required parameter left undocumented anywhere.

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 artifact ('Prepare a human observation note') plus its destination ('caller-owned storage'), which no sibling tool does. Naming 'calculate_relationship_observation' as the required upstream step cleanly separates it from that sibling.

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 a hard precondition (an unchanged calculate_relationship_observation calculation_reference) and marks point/question_id as optional links, so an agent knows the entry conditions. It never frames exclusions as 'use X instead', so routing to alternatives is inferred rather than stated.

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