generate_fridge_magnet

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

With no annotations, the description carries the full burden and does substantial work: it discloses the free-tier quota (3/month), that oversized meshes are auto-decimated for the stage, that a PNG preview is always produced, and that hosted sessions attach a browser stage link. It omits what a quota-exceeded failure looks like and whether a generated magnet is persisted as a design artifact, keeping it short of a 5.

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?

The purpose is front-loaded in the first sentence, which is good. But the final 'INLINE 3D STAGE' paragraph largely repeats the parenthetical in sentence one (orbit/zoom panel in MCP Apps hosts, hosted sessions add a browser stage link), so a whole block is redundant rather than additive.

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 15-parameter generator with no annotations and no output schema, the description does cover the return experience (PNG preview plus interactive stage) and quota limits, which is the most important missing structured data. It leaves the parameter surface entirely undocumented semantically, which is a meaningful gap given the breadth of the 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 description coverage is 100%, so the baseline is 3, but the schema descriptions are only default values ('Default: "PLA"', 'Default: 50.0') rather than semantics. The description adds essentially nothing about the 15 parameters — front vs. back, photo_mask, color_overrides, brief_id, include_step are all left unexplained 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?

The opening sentence names a specific verb and resource: 'Generate a printable fridge magnet with front decoration,' which an agent can distinguish from the many other product generators (generate_coaster, generate_keychain) in the sibling list. It also clarifies its relationship to design_session and compile_scad, though it never explicitly contrasts itself against the sibling magnet tools such as check_magnet_design or generate_magnet_qc_plan.

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 'MAKE DOORS' paragraph gives real routing context (design_session is not installed here; compile_scad is the make → preview → iterate loop), and the free-tier quota of 3/month tells the agent when calls will start failing. However, it never states when an agent should pick this tool over the other product generators or when it should not be used at all, so usage is only implied.

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