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

Annotations already declare readOnly, non-destructive, and closed-world, so the safety profile needs no restating. The description earns credit by disclosing non-obvious return behavior: every figure ships with a source URL and period, verbatim quotes, and a 'not_yet_tracked' sentinel for untracked states that explicitly must not be read as 'nothing changed' — an absence-handling rule an agent could not infer.

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?

Purpose and trigger conditions are correctly front-loaded, but the body pads out with four quoted example questions across two languages and a trailing boilerplate line about market research and 'not medical advice.' Roughly a third of the text could be cut with no loss of routing signal.

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: it names the record contents (adopted change, effective date, verbatim quote or data file, source URL) and the sentinel case. For a 4-parameter, all-optional filter tool, nothing an agent needs to call it correctly is missing.

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; the description goes beyond it by clarifying that from/to filter on effective dates rather than publication dates, and by noting that the state parameter changes result shape (TX lists individual CPT codes for the Sep 2026 rate change). The lang parameter is left entirely to the schema, which covers it adequately.

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 (dated changes in US public dental programs), the two question shapes it answers (what changed, when a change took effect), and the underlying data type (adopted changes with effective dates). This separates it cleanly from siblings like medicaid_adult_dental_rules (current rules) and medicaid_paid_by_code (code-level payment) without needing to open either 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?

Explicit routing on both sides: an affirmative 'use this when the user asks what changed / when a change took effect' plus a 'Do not use for' list covering diagnosis, treatment choice, insurer pricing, dentist recommendations and non-US/Canada geographies. Example user phrasings in English and Spanish further anchor the trigger conditions.

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