Create a profile

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds real behavioral context beyond them: profile-level isolation ('nothing leaks between them'), the dedupe rule that re-running with the same name returns the existing profile, and the fact that creation is free while a following draft costs credits and refuses before charging.

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 core action and alternatives, and the idempotency and cost notes are valuable. It slips slightly: the long inventory of profile-scoped resources (memory, swipefile, Library, avatars, skills, playbooks, connectors) is expendable, and the credit/refusal logic for draft_brand is fairly verbose for a create tool.

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?

No output schema, so the description carries the return semantics and does so adequately (returns the existing profile when the name repeats). With safety annotations present, the description fully covers what an agent needs: purpose, alternatives, isolation, idempotency, and cost prerequisites.

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%, so the baseline is 3, but the description adds meaning to both parameters: 'switch to it' clarifies that activate defaults to making the new profile the active scope, and the name-based dedupe semantics change how 'name' behaves on repeats (returns an existing profile rather than erroring or duplicating).

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 precise verb + resource ('Add a NEW profile') and enumerates what counts as a profile (brand, client, creator, personal workspace), which no sibling tool does. It explicitly distinguishes itself from draft_brand and update_brand, so an agent can pick it without opening any 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 explicit when-to-use routing: use draft_brand to FILL the profile and update_brand to EDIT it, with this tool only creating. It also states the prerequisite (credits for the subsequent draft, ~100) and the failure mode when the requirement is unmet, which is the kind of guidance agents need before invoking.

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