find_field_references

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

Annotations include readOnlyHint=true and openWorldHint=true, and the description complements rather than contradicts them. Beyond annotations, it discloses that script matches are substring (LIKE) based with false-positive/miss risks, and that results are candidate lists. Only minor gap: it doesn't describe return format or pagination behavior, but with read-only annotations covering safety, this is strong coverage.

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?

Two sentences, no filler. First sentence delivers purpose and scope; second sentence delivers usage guidance and caveats. Every clause earns its place with actionable information. No repetition of schema content or annotation hints.

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 read-only search tool with full schema coverage and good annotations, the description is complete. It explains what it searches, when to use it, how matches work, and their reliability. No output schema exists, but the caveat about candidates-not-definitive compensates for what a return-type spec might otherwise need to communicate.

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 100% (field, limit, table all documented in schema). The description's main param contribution is explaining the 'limit' semantic ('Max matches per source'), adding per-source meaning beyond the schema's generic default note. This adds modest value on top of a fully-covered schema, warranting the baseline 3.

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?

Clear verb+resource: 'Find where a table field is used' — specific and unambiguous. It enumerates the exact artifact types searched (dictionary entry, business rules, script includes, client scripts, UI actions, widgets), which distinguishes it sharply from sibling `find_script_references` (script-only) and `discover_table`. The purpose is fully specified with scope and intent.

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?

Provides explicit context: 'Use it before renaming or removing a field.' This is a concrete, actionable trigger condition that tells the agent exactly when to invoke. It also clearly explains the match semantics (substring/LIKE) and caveats (false positives from comments, similarly-named symbols; misses for dynamically-built references), and instructs treating results as candidates to review not a definitive list. This is model usage guidance.

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