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

Annotations already establish readOnly/idempotent/closed-world, and the description adds genuinely new behavioral context: the read is scoped to the attorney's own workspace, the hint is generic rather than the attorney's real fields, and HIPAA details may be present in the return. It does not cover failure modes (unknown id, unapproved note), which keeps it from a 5.

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 access constraint and resource are front-loaded, and the long enumeration earns much of its space because no output schema exists — this is the only place the agent learns what comes back. It is one very dense run-on sentence, which costs a point on structure.

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 carries the return-value burden and does so thoroughly (structured record, approved narrative, mapping hint), plus auth tier, tenancy scoping, and a guardrail against blind field writes. An agent has everything needed to call it and use the result responsibly.

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, but the description adds meaning beyond the schema: it explains what the target_system mapping hint actually is (common place names, not the attorney's actual fields) and that the default is the attorney's chosen system. It also ties 'id' to its provenance, though the schema already says 'from list_hearing_notes.'

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 resource and scope: 'One hearing note from the attorney's own Pro Workspace,' then enumerates exactly what the record contains (outcome lines, awards, WCB status, to-dos, narrative, mapping hint). This is clearly distinguishable from list_hearing_notes and mark_hearing_note_posted without opening any schema.

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 access precondition ('Signed-in Pro or Firm attorneys only') and strong downstream usage instructions: show the attorney a preview and ask before writing anything, and 'Never fill a field the note does not have.' It does not explicitly contrast with the siblings (e.g. use list_hearing_notes to find the id, mark_hearing_note_posted after posting), so it stops short of full when/when-not routing.

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