find_models

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely non-obvious behavior: the default exclusion of ir/reverb kinds, that `installed` can be null when the pedal couldn't be checked, and that `inspired_by` should only be trusted as far as `notes` supports. These are meaningful trust and scoping caveats beyond the 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?

The parameter-by-parameter layout is easy to scan and front-loads the purpose. The closing instructions about writing `index` to `param` on `block` or `file` to `param` belong to set_block_params rather than a search tool, and they dilute the otherwise tight prose.

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?

With an output schema present, the description need not explain return values, yet it usefully adds caveats about `installed` and `inspired_by` reliability. The only real gap is the undocumented `limit` parameter, which matters for an agent paging large model libraries.

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 0%, so the description carries the burden, and it does explain `query` semantics, enumerates `kind` values (block, amp, cab, mic, clone, superclone, nam, ir, reverb), and describes `category` as a block filter. But `limit` is never mentioned, and `installed` is described as if it were an input filter when it is not in the schema — a detail that could mislead an agent into passing an unsupported argument.

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 opening sentence gives a specific verb and object set: 'Find blocks, models and files by name or by the gear they're inspired by,' which lets an agent distinguish this search tool from list_blocks or describe_block. It does not explicitly name a sibling alternative, so it stops short of a 5.

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?

There is real conditional guidance — 'ir and reverb are only searched when asked for' tells the agent these kinds are excluded by default. However, nothing says when to use find_models versus list_blocks, list_block_presets, or describe_block, so the sibling routing is left to inference.

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