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

Goes far beyond the annotations: discloses the billing model (usage per matched record only, derived-only rows free, amount_charged is a pending estimate not an invoice), the 'creator' scope requirement, and the non-obvious semantics of iag_person_id (org-scoped, non-reversible, best-effort derived id on unmatched rows — use match_count/record_count rather than id-presence to distinguish). It also explains the independent resolution_action and license_action axes with a concrete combined case.

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 purpose and return contract are front-loaded, which is good, but the body collapses into a single dense run-on paragraph mixing billing, ID semantics, action enums, and filtering advice. The sentence "Include I in match_level for direct ID lookup, or omit the filter" is cryptic and buried mid-paragraph where it is easy to miss.

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?

Despite an output schema existing, the description supplies the interpretation layer that the schema cannot: what each action value means, how the two action fields interact, and how to determine real matches from derived rows. Scope requirements, billing caveats, and the scale-up alternative are all covered, leaving nothing an agent needs to call this correctly.

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 still adds real meaning on top: it clarifies that a tier-01 Person ID from a prior real match can go straight to Refresh while an audience-only ID has null match_level, and gives guidance on match_level filtering. The remaining parameters (template_id, spatial_mode, field_list) are left entirely to 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?

Opens with a specific verb and resource ("Perform real-time identity resolution on up to 100 records") and immediately establishes the scope limit and the inline-record input shape. It is clearly distinct from sibling tools like create_segment and get_match_run, which it names as complements rather than substitutes.

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 an explicit routing rule for large batches ("more than 100 records, use create_segment(subtype=\"matched\") with a file upload instead") and points to get_match_run for later retrieval. It also warns that an active license avoids another identity-license charge. It stops short of contrasting against other match-adjacent siblings such as deliver_file_match or list_match_runs, so it is strong but not exhaustive.

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