price-compare

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

Annotations already declare the tool read-only and idempotent, so the description is not required to restate that. It adds the scope 'full published pricing' but does not address errors, rate limits, or data freshness. No contradiction with annotations.

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 description is one short, front-loaded sentence with zero filler. Every word earns its place by identifying the action, scope, and return content.

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-parameter, read-only tool with no output schema, the description is complete: it names the input (provider id), the output (details and pricing), and the scope (one provider). Annotations cover safety characteristics, leaving no significant gap.

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 100% and the id parameter is already described as 'Provider id, as returned by search_providers'. The description only restates that the lookup is by provider id, adding no new semantic information 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 uses the specific verb 'Get' and names the exact resource: 'one provider's details and full published pricing' keyed by provider id. This clearly differentiates it from search_providers, which is for finding providers rather than retrieving one by id.

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 'by provider id' together with the schema's hint that the id comes from search_providers implies the correct workflow: search to obtain an id, then call this tool for details. It provides clear context, though it does not explicitly mention alternatives or exclusions.

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 readOnlyHint and idempotentHint, and the description does not contradict them. It adds useful behavioral context by specifying what the returned list contains (medicines, lowest published monthly price, and provider count), which is especially valuable given there is no output schema.

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 description is a single well-structured sentence with no filler. It front-loads the primary action and resource, then efficiently adds the key output details and examples of included medicines in parentheses.

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 zero-parameter, read-only list tool, the description is largely complete: it names the medicines, the comparison context, and the returned data points. It could slightly improve by noting currency or sorting, but given the tool's simplicity, nothing critical 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?

The tool has zero parameters and the schema description coverage is 100%, so there are no parameter semantics to clarify. The description's mention of the output fields is the only relevant semantic information, and it provides sufficient 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 specific verb ('List'), a clear resource ('UK weight-loss medicines compared on WeightMedsCompare'), and the exact output fields (lowest published monthly price and number of providers). This clearly differentiates it from sibling tools like get_provider or search_providers, which focus on individual providers rather than the medicine list.

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 description implies when to use the tool: when the agent needs an overview of all compared weight-loss medicines with prices and provider counts. However, it does not explicitly state when not to use it or how it compares to the sibling tools, leaving the routing decision 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 declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context: the ranking is based on an objective score, an eligibility note is optional, and the tool does not produce medical advice. This goes beyond the structured hints and gives the agent a clearer mental model of the tool's 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?

Two sentences with no filler. The core purpose, scoring basis, optional note, and important caveat are all packed efficiently, with the ranking behavior front-loaded.

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 7 parameters, no output schema, and sparse schema descriptions, the description needs to explain the ranking inputs and return shape. It provides the overall intent and caveats but does not explain the meaning of key parameters (bmi, monthly_budget_gbp, weight_related_condition, format) or what the returned ranked result looks like. An agent would struggle to invoke this tool correctly for nuanced cases.

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 only 43%, and the description must compensate but largely does not. It mentions price, rating, and CQC registration as score inputs, which loosely maps to monthly_budget_gbp, cqc_registered, and medication, but it says nothing about bmi, format, weight_related_condition, or limit. The description does not help an agent understand how these parameters influence ranking or eligibility.

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 names a specific verb ('Rank'), a resource ('UK providers'), and a clear selection criterion ('objective score' based on price, rating, CQC registration). It also differentiates itself from siblings by framing this as comparison rather than retrieval or search, so an agent can distinguish it from get_provider, list_medicines, and search_providers.

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 description gives a clear use context: ranking multiple providers for a medicine, with an explicit disclaimer that it is not medical advice or a recommendation and that a prescriber decides suitability. It does not explicitly name alternatives or state when to prefer search_providers/get_provider, but the ranking-purpose is clear enough to orient an agent.

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 tool read-only and idempotent. The description adds a useful behavioral cue that the data is 'factual listing data, not a recommendation,' and clarifies that the price returned is the lowest published monthly price. It does not disclose data freshness, what 'published' means, or how the listing is constructed.

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 description is two short sentences: the first states the purpose and key behavior, and the second adds an important interpretive caveat. Every sentence earns its place, and there is no filler or repetition.

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?

The tool has no output schema, five parameters, and three undocumented parameter semantics. The description partially explains the return behavior (providers with lowest published monthly price) and uses annotations to cover safety, but it leaves filter meanings and the exact response shape to inference. This is adequate but not complete.

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 only 40%; medication and limit have descriptions, but cqc_registered, published_price_only, and max_monthly_price_gbp do not. The tool description provides no additional meaning for any parameter and does not compensate for the undocumented fields, even though their names are somewhat self-explanatory.

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 ('Find') and identifies a clear resource: UK providers of a weight-loss medicine, with the output criterion of the lowest published monthly price. It is clearly distinct from siblings like get_provider and list_medicines by resource and scope, though it does not explicitly name them.

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 usage context is implied: use this when you need provider listings with price data for a weight-loss medicine, not when you need a recommendation. However, there is no explicit discussion of when to prefer get_provider, list_medicines, or match, and no stated exclusions.

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