build_delivery_url

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world profile, so the safety story is covered. The description adds genuine context beyond that: transforms run on the fly at the CDN and are cached, which tells the agent the result is a derived, reproducible URL. It stops short of saying whether the URL is permanent, how transform errors surface, or that the underlying asset is never mutated.

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 short sentences, front-loaded with the core verb and resource, then the CDN/caching behavior, then two compact examples. Nothing is redundant and the reading order matches what an agent needs first.

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 a 100% documented schema and an output schema present, return values need no explanation, and the description covers what the tool does and how transforms behave. The one real gap is disambiguation from build_signed_url, which the description leaves entirely unaddressed.

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% and every transform field is documented inline, so the baseline of 3 applies. The description only illustrates parameter combinations (width 400 + format webp, format pdf for a Word doc) rather than adding semantics the schema lacks, such as how url must match exactly or what preset does relative to explicit fields.

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?

Uses a specific verb and resource ("Builds a delivery URL") and enumerates the transform capabilities (resize, crop, convert, transform). It is clear what the tool produces, but it never distinguishes itself from the sibling build_signed_url, which an agent could easily confuse with a delivery-URL builder.

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?

Usage is only implied through examples ("width 400 and format webp for a thumbnail; format pdf to convert a Word document"), which do convey intent but not exclusions. There is no statement about when to use this versus build_signed_url, convert_document, or create_preset, all of which sit in the sibling list and are natural alternatives.

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