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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description reveals important behavior: collision returns 'ambiguous' with ranked candidates and never silently picks, type_hint narrows the universe, crypto aliases resolve, and low_confidence is a weak-match signal with explicit advice to verify. This enriches the agent's understanding of runtime responses significantly.

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 informative yet structured: it leads with a clean one-sentence purpose, gives necessary behavioral nuances, then an Args list. Each sentence adds meaningful guidance—no filler. The explicit alternative pointer and the low_confidence example are useful and not redundant.

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?

Given the tool's disambiguation behavior, the description adequately covers its main use case, edge cases (collisions, low confidence), and relationships to companion tools. The output schema exists, so the description need not enumerate return details, but it explains the semantic value that the agent needs for correct invocation and post-result verification.

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 must carry the parameter semantics. The Args section explains query as free-form text and type_hint as an optional namespace narrowing hint, with concrete examples ('equity', 'etf', 'coin'). While the type_hint examples are helpful, the description could be slightly more precise about accepted type_hint values beyond those examples, but it is still well above a baseline because the description compensates for the missing schema descriptions.

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: 'Resolve free text to a canonical market or macro entity.' It clearly explains the tool's output (namespace/ids entity) and its use for get_snapshot/get_timeseries, setting it apart from sibling tools including the compliance-oriented sugra_entity_lookup/screen.

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 alternatives: for compliance KYB lookups use sugra_entity_lookup / sugra_entity_screen instead. It also explains when to use type_hint to narrow an ambiguous resolution and advises verifying low_confidence results. This covers when and when not to use the tool.

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