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

Annotations already cover read-only, idempotent, closed-world behavior, but the description adds real value beyond them: data provenance, the 'no individuals are named' privacy note, facility ordering (lowest share first), and explicit caveats that data is medical-only and penalty figures are the workbook's own calculation. It does not discuss return size or pagination.

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 the subject and source, then parameter semantics, then caveats. Every sentence is informational, but the pipe-delimited level enumeration is dense and a shorter lead sentence would improve scannability.

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 adequately conveys what comes back (required vs reported hours by prison/job/month, penalty rows) and flags interpretation limits. It could say more about returned caveats structure or facility-level record shape, but nothing critical is missing for correct invocation.

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 0%, so the description carries the full burden — and it does: level values are semantically defined, facility accepts a slug, id, or name fragment with an example, position examples ('RN', 'LPN', 'NP/PA') are given, and month format YYYY-MM is specified.

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 with unusual precision: required vs reported medical staffing hours under Georgia DOC's Centurion contract, by prison, job and month, plus penalty calculations. It also names the exact source workbook and request number, making it clearly distinct from siblings like get_facility_staff_roster.

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 level enumeration effectively explains how to select each mode (contract for system totals and penalty rows, facility for one-per-prison ordering, position for job breakdowns, matrix for contracted FTEs), which functions as usage guidance. It stops short of naming when to use a sibling tool instead, and does not explicitly say which level is the default.

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