Find instances

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description discloses important execution behavior: 'Every filter you supply must match' clarifies AND semantics, and 'Tag searches are answered from CollectionService's index rather than by walking the tree, so they stay fast on large places' reveals performance characteristics. It also preempts error handling by advising to narrow with `path` when TOO_BROAD. These details add substantive behavioral context beyond the structured annotations.

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 a well-structured paragraph that front-loads purpose, then explains the AND semantics with a concrete example, then provides routing guidance, performance note, and error-handling tip. Each sentence earns its place; there is no fluff. It is compact yet information-dense, appropriate for a tool with 10 parameters.

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 complexity (10 parameters, no output schema), the description is remarkably complete. It explains the search logic, performance considerations, error handling, and the cost of different detail levels. The annotations already cover safety via readOnlyHint and destructiveHint. An agent has all necessary information to invoke it correctly for a wide range of queries and to interpret potential TOO_BROAD errors.

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 schema already documents each parameter. The description adds meaning beyond field descriptions: it explains that all supplied filters must match (AND logic), which is not in the schema. It also gives cost guidance for `detail` levels ('concise = name + class only, cheapest... full = every readable property, expensive') and hints at error recovery via `path`. This goes beyond a baseline 3 by enriching understanding of parameter interactions and trade-offs.

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 clearly states the tool's function: 'Searches the data model by name, class, property value and/or tag.' It specifies the resources (data model instances) and the exact search dimensions. It also distinguishes itself from siblings by noting it replaces separate search tools and explicitly positioning itself against `tree`: 'Prefer it over `tree` whenever you know what you are looking for.' This makes its purpose unambiguous and separate from other tools.

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 when-to-use guidance: 'Prefer it over `tree` whenever you know what you are looking for.' It also provides troubleshooting advice: 'Narrow with `path` if a search reports TOO_BROAD.' It explains the benefit of combining filters in one call, which clarifies the intended use case for complex queries. While it doesn't enumerate every alternative, it clearly differentiates from `tree` and offers practical direction on when to narrow the search.

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