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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is lower, but the description still adds substantial behavioral context: 'No LLM call' signals cost/latency profile, 'failed_expertises and partial identify incomplete work even when output exists' reveals that a returned record may still represent failed work, and it explains the semantics of fusion metadata and the conditional database_sync field. No contradiction with annotations — 'Read' and 'No LLM call' align with the read-only hint.

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 description is dense but well-structured: core purpose first, then result-interpretation semantics, sibling routing, metadata meaning, and finally cost/docs pointers. Every sentence carries distinct information with no filler, though it is on the longer side and slightly front-loads detail before the simplest 'no LLM call' takeaway.

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?

For a single-parameter read tool with an output schema and safety annotations, the description covers everything an agent needs: what fields the record contains, how to detect incomplete/failed work, which sibling to route to for recovery, what fusion metadata means, the meaning of the conditional database_sync field, and a docs link for interpretation. Nothing essential 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%: the single parameter record_id is already documented as 'UUID of the record.' The description reinforces this via 'one persisted record' but adds no parameter-specific format, validation, or edge-case detail beyond the schema. Baseline 3 is appropriate when the schema carries the full parameter documentation burden.

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?

The description opens with a specific verb-resource pair ('Read one persisted record's...') and enumerates exactly which fields are returned (structured_output, entity_input_data, validation errors, expertise verdicts, metrics). The singular scope 'one persisted record' cleanly distinguishes it from list_records, and the focus on enrichment/verdict data separates it from get_schema and get_stats.

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 description gives explicit routing guidance: 'use retry_expertises only on a record with failed domains', telling the agent when a sibling is appropriate and what precondition must be checked first. It also clarifies interpretation ('failed_expertises and partial identify incomplete work even when output exists') and points to recovery docs. It does not explicitly contrast with list_records or get_stats, but the read-one-record scope implies the boundary.

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