delete_modelRemove a model from the registry. Fails (isError) if the model does not exist.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The model id. |
| Name | Required | Description | Default |
|---|---|---|---|
| deleted | No | True when the model was removed. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the tool is known to be destructive. The description adds the specific error behavior: it will fail (isError) if the model does not exist. This is valuable behavioral context beyond the annotations, clarifying a failure mode an agent would otherwise not anticipate.
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 single, compact sentence that front-loads the primary action and immediately states the error condition. There is no redundancy or wasted wording, making it efficient for an agent to parse.
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 simplicity (one parameter, confirmed destructive hint, and likely output schema indicating success/failure), the description covers the essential behavior: removal and the failure case. It does not mention potential side effects like cascading deletions or required permissions, but for this simple operation with annotations, the description is sufficiently complete.
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?
The only parameter, 'id', has a description in the schema ('The model id.') and the schema description coverage is 100%. The tool description adds no additional semantic detail about the parameter, so it relies on the schema, which is adequate. Baseline 3 is appropriate since schema covers it fully.
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 action: 'Remove a model from the registry.' It specifies the resource (model) and the registry, and adds a failure condition (fails if model does not exist). This distinguishes it from sibling tools like create_model, patch_model, and restore, which involve different operations.
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 implies usage for deletion but does not explicitly contrast with alternatives or provide context such as preconditions, irreversibility, or when to prefer restore over delete. It lacks explicit 'use when' or 'do not use when' guidance, though the purpose is clear enough that an agent could infer the use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but get_audit explicitly subsumes get_history and explain, and get_state with paths overlaps get_field, creating minor selection ambiguity. The detailed descriptions help, but an agent could still reach for the wrong getter.
Naming is overwhelmingly consistent: snake_case with verb_noun structure and coherent get_/create_/delete_ clusters. Minor deviations like bare verbs (mutate, explain, restore, snapshot) and eval instead of evaluate prevent a perfect score.
27 tools is above the comfortable range and feels heavy, especially with several overlapping audit/state getters that could be consolidated. That said, the domain is broad enough that the count is defensible, so it is heavy but not chaotic.
The tool set covers the full model lifecycle well: create, validate, test, mutate, evolve, read, delete, plus snapshot/restore, audit, blobs, views, library, and expression evaluation. Minor gaps like explicit export/import or separate view-management tools are workable around.