Meal Planner — free recipe beta

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value beyond the schema by declaring the output is informational with website links and by naming the actions it will refuse to perform, which helps the agent avoid misusing it for transactions.

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?

A single dense sentence packs the scope and the boundary list; the boundary clause is appropriately front-loaded within it. It is slightly overloaded (four topics plus four prohibitions in one breath) but every clause earns its place.

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 parameters, no output schema, and full annotation coverage, the description only needs to establish scope and safe-use boundaries, which it does by listing covered topics and forbidden actions. Return content (website links) is hinted at, which is adequate for an informational tool.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. Nothing in the text contradicts the schema.

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 description uses a specific verb ('Explain') and enumerates the exact subject matter: free samples, weekly Plus service, the current CAD subscription offer, and the separate authenticated member MCP setup. That is far more concrete than a tautology, though it never explicitly contrasts itself with the recipe siblings.

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?

It defines the usage context (questions about offerings, pricing, and MCP setup) and, unusually, states explicit exclusions: it cannot subscribe, change an account, send groceries, or pay. No alternative tool is named, but the siblings (recipe lookup) do not compete with this scope.

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

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

Annotations already declare the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value beyond them: it enumerates returned content (source quantities, steps, timing estimates, disclosures) and gives a negative guarantee that subscriber recipes and household plans are never returned. It does not say what happens when a slug doesn't resolve.

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?

Two tight sentences, front-loaded with the core action and the lookup key before the exclusions. 'Deliberately free' is slighty awkward phrasing but no sentence is wasteful.

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 single-argument read with strong annotations and no output schema, the description covers what is fetched and what is excluded, which is most of an agent's need. The only real gap is error behavior for an unknown or non-free slug.

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 0%, so the schema documents only that 'slug' is a 1-100 character string. The description supplies the one missing semantic — that it is a *catalog* slug, not a household/subscriber identifier — but adds no format, example, or where-to-obtain-it guidance.

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?

Names a specific verb and cardinality ('Read one complete ... recipe'), the resource, and the exact lookup key ('by its catalog slug'). The closing sentence excludes subscriber recipes and household plans, which separates this from get_meal_planner_info and from the multi-result search_public_recipes.

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: you call this when you already have a catalog slug and need the full recipe. It never explicitly says 'use search_public_recipes to find a slug first' or names the alternatives, so routing between this and its two siblings is left to inference.

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

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description adds genuine context beyond them: 'No account required', not personalized or certified allergy-safe, and that unlabeled weekly recipes are not inferred suitable. It does not, however, explain result set size or pagination behavior.

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 intent is front-loaded with the core verb, but the body is a dense chain of clauses ('Find complete free samples and recent public first-dinner recipes...') that is harder to parse than necessary; several sentences could be tightened without losing meaning.

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 3-parameter search tool with no output schema and only safety annotations, the description supplies substantial behavioral context (diet matching rules, timing semantics, account/safety caveats). The main gap is the unexplained limit parameter and the orphaned timing_basis reference.

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 0%, so the description must compensate. It explains query matching and that max_minutes 'bounds the published estimate', but leaves the limit parameter completely unexplained and references a 'timing_basis' distinction that does not appear as a schema parameter, creating ambiguity rather than clarity.

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 description states a clear verb+resource ('Find ... recipes') and specifies the searchable fields: ingredient/name words and reviewed dietary labels. It is specific about what can be searched and what counts as a match, though it never names its siblings (get_public_recipe, get_meal_planner_info) to differentiate itself.

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?

It gives real query semantics — all diet/ingredient words must match, neutral words like 'dinner'/'with' are ignored, and an exact title is treated as a name lookup rather than a dietary filter. However, it offers no guidance on when to use this search versus the sibling get_public_recipe for a single lookup, leaving the routing to inference.

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