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

With no annotations, the description carries the full burden and does disclose a key behavioral trait: the full compact list is about 30 KB, warning the agent of a large payload and prompting it to scope. It doesn't cover caching or whether output is static, but the size disclosure is genuinely useful and not derivable from structured fields.

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?

Three sentences, no waste, and the enumeration of content comes first followed by the size warning and the remedy. Front-loaded and every sentence earns its place.

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?

There is no output schema, so the description must characterize the return value, and it does (fields with types, ranges, operators, example filters plus the 30 KB size). For a read-only introspection tool with no annotations, this is nearly complete, only missing minor notes on freshness/static nature.

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%, so the schema already documents query, detail, and prefix with examples. The description's 'narrow it with prefix or query' largely restates that, so baseline 3 is appropriate with little added meaning.

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?

States a specific verb and resource ('Every filterable ontology field') and enumerates exactly what is returned (type, range/allowed values, shortcut names, operators, example filters). It ties the resource to its consumer ('for search_inventory'), which differentiates it from the adjacent get_ontology sibling.

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 practical usage advice on how to call it ('narrow it with prefix or query'), which is real guidance. However, it never states when to reach for this vs. get_ontology or the other introspection siblings, so the when-to-use-vs-alternative decision is left implicit.

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