pricing

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description goes further with what an agent actually needs: nothing is purchased, reserved, or charged, a free PDF proof is emailed before printing, and constraints of minimum 25 sets and 1-150 titles apply. This is real side-effect disclosure beyond the annotation set.

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 trigger and the return value, then packs constraints and exclusions into the remaining sentences with no filler. Dense but every clause carries routing or constraint information; only the parenthetical stacking makes it slightly heavy.

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, yet the description explains what comes back (exact price plus a pre-filled designer orderUrl) and the review/checkout flow. Combined with the exclusions and limits, an agent has everything needed to call this correctly and to know it commits nothing.

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 description's numeric limits (25 sets minimum, 1-150 titles) and the options-map hint duplicate what the schema already says. It adds no format or syntax detail beyond the structured fields, so the baseline 3 for fully-documented parameters is correct.

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 (draft) and resource (custom tab order) plus the concrete return artifacts: an exact price and an orderUrl that pre-fills Tabzoola's designer. This clearly separates it from quote_price (quotes for edge cases) and get_pricing_capabilities (option lookup), so an agent can route without opening a 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 trigger ("when the user has their actual list of tab titles... and wants an order drafted") and explicit exclusions ("Do not use for reverse-printed tabs, PMS ink or custom sheet sizes (quote only)"), effectively routing those cases to the quote sibling. When-to-use, when-not-to-use, and the alternative are all present.

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 readOnly, idempotent, non-destructive, and closed-world. The description adds that the tool takes no input and enumerates what it returns (products, option keys and choice ids, valid set quantities, ordering facts), which is useful beyond the annotations. It stops short of describing output format or caching, so not a 5.

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 plus a short exclusion sentence, with the call-to-action ('Use this first') front-loaded. Every clause carries distinguishing information—product scope, return contents, and exclusions—with no 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?

For a zero-input, read-only discovery tool with no output schema, the description supplies the return contents, the sequencing relative to siblings, and the exclusion boundary. An agent has everything needed to select and call it correctly.

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 and the schema is empty with additionalProperties false, so there is nothing to disambiguate; the description's 'Takes no input' correctly confirms this. Baseline of 4 applies for a parameter-free tool.

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 (returns pricing capabilities: products, option keys/choice ids, set quantities, ordering facts) and scopes it to the exact product family (custom-printed index tab dividers), with parenthetical synonyms so the agent can match user phrasing. This is clearly distinguishable from quote_price and draft_order.

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?

Explicitly says 'Use this first, before quote_price or draft_order' when the user wants dividers priced or ordered, naming both siblings and the ordering relationship. It also states a negative boundary: not for blank/write-on dividers, labels, or binders.

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 readOnly/idempotent/non-destructive, so the 'Read-only; purchases nothing' line is largely reinforcement. However, the description goes well beyond annotations by disclosing return contents — section titles in order, tabs per set, the describing page, the 25-set price basis (paper, collated, 3-hole punched, setup included), and an orderUrl that opens a pre-filled designer. That is genuinely useful behavioral context for deciding whether a follow-up call is needed.

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 usage trigger is front-loaded and the closing routing sentence is tight. The opening sentence is long and parenthetical-heavy, but each clause (examples, return fields, price basis) carries information an agent needs.

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, yet the description enumerates the return fields well enough that an agent knows what it will get and when to escalate to draft_order or quote_price. Nothing material is missing for a two-parameter read 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?

Schema description coverage is 100%, so both parameters (query, limit) are already documented in the schema, including the 'omit to list sets' behavior. The description adds no syntax or matching semantics beyond what the schema states, 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 (list/return) and resource (Tabzoola's ready-made named tab sets) and pins the trigger condition precisely: 'when the user names a kind of binder rather than listing titles.' The concrete examples (estate planning, exhibit 1-25, HOA, IEP) make it unmistakable versus sibling tools.

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 when-to-use condition and names the alternative path: 'Pass the titles to draft_order or quote_price for other quantities or options.' That directly routes the agent between this tool and its two siblings with no inference required.

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 readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses the exact return payload (per-set and total USD with setup included, plus an orderUrl that opens Tabzoola's configurator with the build pre-selected for a human), notes pricing parity with the website, and restates the read-only nature in the context of charging.

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 trigger condition and then layers returns, limits and exclusions with no filler sentences. The opening clause is long and clause-heavy, but every element earns its place and nothing is repeated.

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 carries the return-value burden and does so fully (per-set price, total, setup included, orderUrl behavior), plus the hard limits (min 25 sets, 1-150 tabs) and the human-completion handoff. An agent needs nothing else to call this correctly.

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 parameter and the baseline is 3. The description reinforces product (paper or poly), tabs-per-set, sets and the 25-set minimum, but adds nothing about the 'options' map or 'colorChanges', so it does not exceed the schema's own detail.

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+resource ('quote a price for custom-printed tab dividers') and pins the exact inputs required (product, tabs per set, number of sets). It is clearly distinguishable from siblings draft_order (which would transact) and get_pricing_capabilities (which enumerates options).

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 when-to-use condition ('when the user wants a price ... and knows the product, tabs per set and number of sets'), explicit exclusions ('Do not use for reverse-printed tabs, PMS ink or custom sheet sizes'), and an explicit never ('never to charge anyone'). This is close to the when/when-not/alternative bar.

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