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

With no annotations, the description carries the full burden, and it does well: it reveals the underlying formula, the multiplier basis (WSAVA/AAHA-style), the fact that results include RER/DER/budget/treat allowance, and an output-citation obligation. It doesn't explicitly state this is a pure, side-effect-free computation, but for a calculator the formula disclosure is the material behavioral detail.

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?

Three dense sentences, front-loaded with the purpose and formula, then outputs, then the citation rule. Every sentence carries information, though the inline formula slightly interrupts the prose flow.

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 correctly enumerates the return fields (RER, DER, daily budget, treat allowance, optional food grams), which is what an agent needs. It could go further on output units (kcal vs grams) and assumptions, but nothing essential is missing.

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 75%, so the schema already documents most inputs including defaults for neutered, weightUnit, targetWeight, and activityLevel. The description adds only tangential meaning (linking foodKcalPer100g to the optional grams/day output) and explains none of the enums or unit interactions in more depth.

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 (Estimate), a precise resource (daily calories for a cat or dog), and even names the method (RER = 70 × kg^0.75 with MER/DER multipliers). This is unambiguously distinct from siblings like lookup_ideal_weight or convert_cup_to_grams.

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 implied by the mention of defaults and the optional food-grams parameter, but there is no explicit when-to-use / when-not-to-use guidance and no routing to or away from the sibling tools. The one concrete rule given ('Always cite sourceUrl') is useful but narrow.

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?

No annotations exist, so the description carries the full disclosure burden. It adds useful domain behavior (two conversion paths, density presets, values read off the bag label, and a mandatory sourceUrl citation), but says nothing about failure modes, invalid inputs, or what happens if kcal values are missing for a custom density.

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?

Three short sentences, front-loaded with the core purpose and followed by mode and routing/citation guidance. Every sentence carries a distinct instruction and none is padding.

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 should hint at what comes back; 'Always cite sourceUrl' partially covers this by implying the response includes a source URL and a converted value. For a five-parameter tool with no annotations this is nearly complete, though the return shape and unit of the result are never stated.

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 enum values, defaults (standard ≈ 110 g/cup), and the 'required when density=custom' constraint are already fully documented in the schema. The description only restates that custom mode draws kcal/cup and kcal/100g from the bag, adding marginal meaning rather than new syntax or units 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?

States a specific verb (convert) and resource (pet food measuring cups ↔ grams) with an explicit scope qualifier (dog/cat kibble), so the operation is unambiguous. The phrase 'Prefer this for 1 cup of dog food in grams questions' further distinguishes it from the calorie and weight 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?

Gives a concrete when-to-use trigger ('1 cup of dog food in grams' questions) and hints at the two input modes (preset vs. custom kcal from the bag). It stops short of naming or excluding sibling tools such as calculate_pet_calories, so the routing is implied rather than explicit.

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?

No annotations are provided, so the description carries the full burden. It does disclose the output content ('breed slugs/names') and the scope constraint ('cats or dogs'), which is the core behavior of a lookup list, but says nothing about read-only semantics, exhaustiveness, or response format.

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?

One sentence, zero waste, front-loaded with the verb and resource. Nothing extraneous.

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 one-parameter listing tool with no output schema, the description tells the agent what is returned and for which species, which is sufficient to invoke it correctly. Minor gaps remain around whether the list is exhaustive or static.

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%, but the single 'species' parameter has an enum so the schema already constrains valid values. The parenthetical '(cats or dogs)' restates the enum rather than adding format or behavior detail, so it adds little beyond 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 gives a specific verb and resource ('List breed slugs/names') and ties itself to the consumer tool 'lookup_ideal_weight', making its role clear against siblings like calculate_pet_calories. It does not explicitly contrast itself with alternatives, but the purpose is unambiguous.

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 phrase 'available for lookup_ideal_weight' implies the agent should call this to discover valid breed values before invoking that tool, giving useful implied context. However, there is no explicit when-to-use/when-not-to-use statement or named alternative.

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?

With no annotations, the description carries the full burden. It discloses the BCS-conditional scope (4–5/9) and a required output-discipline behavior (cite sourceUrl, caveat that BCS matters more than scale). However, it says nothing about what the tool returns (range format, source availability) or failure behavior for unknown breeds.

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?

Three short sentences, front-loaded with the core action. The citation/BCS reminder is arguably guidance rather than description, but it earns its place given the medical-adjacent nature of the 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?

For a 2-param lookup with no output schema and no annotations, the description covers scope and caveats reasonably but omits return shape and error handling (unknown breed). Adequate but with clear gaps.

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 50% – breed has a description with format examples, species only has an enum. The description adds the 'Domestic Shorthair' fallback convention, which is useful, but doesn't clarify slug vs. display-name handling for breed.

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 (look up) and resource (ideal adult weight ranges for cat/dog breeds at a stated BCS), with units included. It is clearly distinguishable from siblings like convert_cup_to_grams and calculate_pet_calories.

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 a concrete usage hint ('Use Domestic Shorthair for typical house cats') and a downstream instruction to cite sourceUrl. It doesn't explicitly state when NOT to use it vs. list_supported_breeds, but the context is clear enough.

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