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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false), so the description is freed to add what they cannot: it states the auth requirement ('an access token that can read and change your records') and discloses that the call returns the computed unity formula. It omits that non-idempotent saves will create duplicate recipes on retry, which is the one behavioral gap.

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-loads the core action and outcome, then adds the guardrail and auth note last. Four sentences with little waste, though the repeated 'as the recipe page does / as the recipe page chooses it' phrasing is slightly redundant filler.

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 no output schema, the description usefully says the answer carries the unity formula, and it states the auth requirement for a mutation tool. Remaining minor gaps (duplicate-creation on retry, what the answer contains beyond the formula) are small against a 7-parameter tool whose schema is fully described.

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 schema already documents every field, including the library-name-vs-own-analysis distinction and the firing band cones. The description restates the parameter set at a high level ('base materials and amounts... optional colorants, notes, firing band and food-surface mark') without adding syntax or format meaning, so the baseline 3 applies.

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 and resource ('Saves a new glaze recipe in your Glazecalc account') and scopes what the recipe is built from (base materials and amounts, optional colorants/notes/firing/food-surface). The word 'new' cleanly separates it from the sibling update_recipe, so an agent can pick it without opening the 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 an explicit usage constraint: 'Save only a recipe the person asked to save,' which rules out speculative writes. It does not name update_recipe as the alternative for existing recipes or state any prerequisite beyond the token, so it falls short of full when/when-not routing.

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