Tuper templates

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description still adds real behavior: it discloses which fields are matched (names, who each is for, tab names) and the ranking rule (free versions first when one exists). That ranking detail materially changes how an agent should interpret result order and is not in any structured field.

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 tight sentence-plus-clause, front-loaded with the action and immediately followed by examples and the ranking rule. No filler; every clause carries information an agent can act on.

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 simple two-parameter read tool with safety annotations and no output schema, the description covers what is searched and how results are ordered, which is close to sufficient. The only meaningful omission is the limit parameter's behavior and default, so an agent may not realize how many results to expect.

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%: query is described as 'Trade, job or need' and limit is undocumented. The description enriches query with concrete example terms and the fields matched, which is genuine added meaning, but it says nothing about the limit parameter or default result count, leaving that gap unfilled.

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 ('Find templates') plus the facets searched ('by trade, job or need') with concrete example queries. It is clearly a search tool, though it never names the siblings list_templates or get_free_template, so the boundary with them must be inferred from the 'free versions first' clause.

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 example queries ('landlord', 'bakery', 'stocktake') imply the kind of keyword search this is for, giving an agent a usable usage signal. There is no explicit statement of when to prefer this over list_templates or get_free_template, so routing guidance is implied rather than stated.

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 openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the response is https download URLs, the file type is .xlsx, a filled example file is included only when it exists, and the free-only scoping rule is enforced server-side. It does not cover failure behavior for an unknown id, but that is a minor 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?

Two sentences, no filler, with the return value and the free-only constraint front-loaded. The second sentence is slightly redundant with the first's "free template" framing but reinforces a constraint worth stating.

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?

There is no output schema, so the description carries the burden of describing returns — and it does, naming the URL format, the .xlsx type, and the conditional example file. Combined with a single fully-documented parameter, an agent has what it needs to call this correctly; only error-case behavior is unaddressed.

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 single parameter is documented, so the baseline is 3. The description earns extra credit by enumerating concrete accepted value forms — a free template id with the full slug shape, or a trade name like "landlord" or "invoice" — which materially helps an agent construct a valid call.

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 opens with a specific verb and resource: it returns https download URLs (.xlsx plus a filled example) for one free template. Concrete id examples ("free-rental-property-spreadsheet", "landlord", "invoice") make the resource unambiguous. It does not explicitly contrast itself with find_template or list_templates, so sibling differentiation is only implicit in "one free template".

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 rather than stated: the agent can infer it needs a known id or trade name, and the line "Only files already free on tuper.app/templates/free/ are returned; paid files never are" acts as a when-not constraint. However, no alternative is named for the paid-template case or for discovering an id, even though find_template and list_templates exist as siblings.

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 openWorldHint=false, so safety is covered by structured data. The description usefully discloses the return payload fields and notes the bundle price is included, but says nothing about ordering, result size, or whether the catalogue is exhaustive — the remaining behavioral gaps are minor for a read-only list.

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 front-loaded sentence that leads with the resource and puts the field list and filter note in a sensible order. Dense but no wasted sentences; the field enumeration is long but each item earns its place by telling the agent what comes back.

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, read-only list tool with no output schema, the description adequately compensates by enumerating the returned fields. Missing only ordering/pagination expectations, which is a small gap at this complexity.

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 description must carry the load, and it only says "Filter by access" — effectively restating the parameter name. The enum (all/free/paid) and default are self-explanatory in the schema, but the description adds no meaning about how filtering interacts with the returned bundle price.

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 resource (Tuper spreadsheet templates) and enumerates exactly what each entry contains (name, audience, tabs, USD price, free/paid, page URL, Polar buy link), which makes clear it is a catalogue/listing operation. It does not, however, contrast itself with siblings find_template or get_free_template, so the agent must infer the difference.

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?

"Filter by access" implies the browsing-and-filtering use case, but there is no explicit statement of when to use this instead of find_template (search) or get_free_template (free retrieval). Usage is inferable but not routed.

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