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

The annotations already signal a non-read-only, non-idempotent operation, and the description adds concrete behavioral context: creating the same filter twice yields two filters, no existing filter is modified, and retries after uncertainty should be avoided. This adds real value beyond the annotations rather than contradicting them.

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?

Every sentence earns its place: purpose and translation duty, explicit trigger condition, edit/delete routing, and non-idempotency warning. It is compact enough to read quickly while conveying all operation-critical guidance.

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 complex create operation with nested parameters, an output schema, and annotations, the description covers the ambiguous natural-language-to-numbers mapping, the no-edit/delete limitation, and the duplicate risk. Nothing needed for correct invocation is missing; response shape is already supplied by the output schema.

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% and each parameter has a description, so the baseline is high. The description still adds useful semantics by instructing the agent to translate look descriptions into adjustment numbers, to include only what the operator asked to change, and to treat omitted adjustments as neutral. That is valuable but not essential given the schema's already detailed parameter docs.

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 names a specific verb and resource: create a new photo filter on the operator's account from a natural-language description. It also distinguishes itself from siblings by explicitly stating there is no edit/delete tool, so an agent won't confuse this with duplicate_project or preview_filter.

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?

It gives an explicit trigger condition — 'Call this only when the operator asks for a filter to be CREATED' — plus an explicit exclusion: it does not change an existing filter and edit/delete requests should be sent to the dashboard. It also advises against retrying calls that may have gone through, which is directly actionable.

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