set_blendspace_properties

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

Goes well past the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=true) by disclosing that only supplied fields change, that changes happen in one undo transaction followed by a save, the exact no-op outcome (changed=false, applied_count 0, saved=false, nothing modified), and the failed-save outcome (saved=false, save_error). It even enumerates the return payload, which matters because there is no output schema. The only nit is that 'success false' is mentioned while 'success' is absent from the enumerated returns.

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?

Front-loaded with the purpose and the sibling differentiation, then no-op and failure semantics. It is dense with long compound sentences and a returns enumeration that is partly redundant with the schema's parameter names, but with no output schema that enumeration does earn 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?

For a mutation tool with no output schema this covers the essentials: partial-update behavior, transaction scope, no-op detection, save failure, and the return shape. Gaps are minor: no statement about what happens on an invalid blend_space_path (error vs success=false-everywhere) and no interaction with the explicit begin_transaction/end_transaction siblings despite the mentioned undo transaction.

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 baseline is 3; the description earns above baseline by explaining that unspecified fields are untouched (partial-update semantics) and that y_axis_* is silently noted-and-ignored on a 1D blend space, which the schema does not convey. It stops short of adding value constraints (e.g. min<max) or units.

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 plus the exact fields it edits: 'Configure an existing blend space's X and (for 2D) Y axis: name, min, max, grid divisions.' It explicitly separates itself from the sibling create_blend_space ('create_blend_space only sets X; this sets the Y axis too'), so an agent can route between them without opening either schema.

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 clear context: use it on an existing blend space to change Y (and X after creation), versus create_blend_space which only sets X at creation. It also resolves the 1D-vs-2D decision by saying y_axis_* params are noted and ignored on a 1D blend space. No explicit exclusion list beyond that, so 4 rather than 5.

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