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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds real behavioral context beyond that: embedding rights are checked, the font is sanitised and subset, licence is a user attestation, and the call is project-scoped and returns project identity. It stops short of saying what happens on a rejected or unlicensed font.

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?

Short and front-loaded: the PROJECT-SCOPED constraint leads, then the purpose, then the semantic notes for licence/attest. Every clause carries information and nothing is padded.

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 mutating tool with no output schema, the description covers scope, side effects, licence semantics and the return of project identity. Remaining gaps (error/rejection behavior, what family does) are modest given the annotations already establish the safety profile.

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 only 20% (project_id), so the description must carry the load. It does explain licence (OFL/Apache/commercial, a statement of user rights) and attest (confirms the licence claim), which is genuine added meaning, but asset_key and family remain undocumented in both places.

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 (validate/import) and resource (user-uploaded brand font, TTF/OTF asset) plus the downstream purpose ('so typeset can set it'). An agent can distinguish it from generic asset tools like list_assets or upload_start, though no sibling is named explicitly.

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 condition of use is implied ('a brand font the user uploaded'), and the dependency on set_typeset is hinted at, but there is no explicit when/when-not statement or named alternative. An agent can infer the context but must reason about it.

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