AI Rollout Framework

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds value beyond that by managing output expectations: it explicitly says it returns no numeric score or breakdown, that it returns a stage plus next step, and that it links out to the full site assessment with a PDF. It does not surface the no-guessing rule as a constraint on its own behavior explicitly enough to reach 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?

Three sentences, front-loaded with what the tool does, then outputs, then the negative disclosure ('returns no numeric score'), then the usage instruction. Every sentence carries distinct information with no repetition of the schema.

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 16 required parameters and no output schema, the description carries the return-value burden and does so (stage, next step, link, explicit absence of a numeric score). Combined with the instruction to source answers from the user rather than inventing them, an agent has everything needed to call and use 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?

Schema coverage is 100% — all 16 question texts and the 1-5 rating scale are already documented per-property. The description only restates the 1 = Strongly Disagree / 5 = Strongly Agree scale, adding no syntax, ordering, or interpretation guidance beyond the schema, 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 and resource: it runs the 16-question AI Readiness Score on the user's behalf. It also names the exact return artifacts (readiness stage, next step, link to the full assessment), which makes it unmistakable against the informational siblings like get_faq or get_pricing.

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 clear process instruction — 'Ask the user the questions; do not guess answers' — so the agent knows the interaction pattern (collect 16 ratings first). It does not name alternatives or exclusions (e.g., when a user should take the free on-site assessment instead), so it falls short of a full when/when-not statement.

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 cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), and the description adds context they do not carry: the address is added to a mailing list as a persistent side effect, and the user can unsubscribe from the first email. That is exactly the kind of irreversible/outward-facing consequence an agent needs disclosed.

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-loaded with the purpose, then the constraints, then the side effect – a sensible order with no filler. The closing clause 'sends the kit by email' partly repeats the opening sentence, which is the only wasted space.

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 annotations present and no output schema required, the description covers purpose, gating, and side effects adequately for a two-parameter tool. It stops short of saying what happens on a malformed or already-subscribed address, which is a minor remaining 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 description coverage is 100%, and the schema already explains both 'email' and the 'consent' boolean in detail. The description reinforces the consent rule but adds no syntax, format, or validation detail beyond what the schema states, so the baseline of 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 and resource ('Emails the free Briefing Kit to an address the user gives you') and immediately distinguishes the tool from the content-retrieval siblings by naming the delivery mechanism. An agent can tell this is an outbound email action rather than a fetch-a-document call.

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?

Explicit when-to-use ('only when the user has explicitly asked to receive it by email and agreed to be emailed') and explicit when-not ('Never call it on your own and never invent or guess an address'). The gating condition is unambiguous, so an agent cannot mistake this for an autonomous action.

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, idempotentHint, openWorldHint=false and non-destructive, so the safety profile is covered. The description adds genuine scope boundaries by naming excluded content (transcripts, quiz content), which helps an agent avoid a wrong tool call, though it says nothing about freshness or whether the outline is subject to change.

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 what is returned, followed by the usage condition and the exclusion/alternative. Every sentence carries distinct routing information 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?

No output schema exists, yet the description enumerates the returned fields (modules, inclusions, seat tiers, guarantee), so an agent knows what to expect. With no parameters and annotations covering the safety profile, nothing needed to call this correctly 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 takes zero parameters, so per the rubric the baseline is 4. There is no parameter syntax for the description to explain, and it correctly does not invent any.

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 the public outline of AI at Work') and enumerates exactly what the payload contains: modules, inclusions, seat tiers, guarantee. This is clearly distinguishable from siblings like get_pricing or get_faq, which cover adjacent but different content.

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 names the use case ('questions about employee training'), states what it will not serve ('does not return transcripts or quiz content'), and routes the agent to the correct alternative ('To check readiness, use assess_ai_readiness'). When-to-use, when-not-to-use, and 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, closed-world behavior, so the safety profile is covered. The description adds the meaningful constraint that only *published* items are returned, which is not derivable from the annotations. It stops short of describing result shape or ordering, but the bar is lower given full annotation coverage.

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 sentences, front-loaded with the core behavior, followed by routing guidance and one negative constraint. No sentence is redundant and nothing important is buried.

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 lookup with full annotation coverage and a fully documented schema, the description supplies everything an agent needs: purpose, scope limit (published only), filter semantics pointer, and explicit alternatives. The absence of an output schema is not a meaningful gap for a Q&A list 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% and the schema itself is unusually rich, enumerating the valid category values and explaining the free-text fallback and the omit-to-get-all behavior. The description only restates 'optionally filtered by topic', adding nothing beyond the schema, 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 and resource ('Returns published questions and answers') plus the optional filter, and explicitly contrasts itself with search_knowledge_base and assess_ai_readiness. An agent can distinguish it from all eight siblings 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 explicit when-to-use ('specific questions about pricing, governance, implementation or the products') and when-not ('does not search the long-form guides'), naming the replacement tool. It also routes readiness checks to assess_ai_readiness, covering the nearest ambiguous 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 readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine scope context by naming what is returned and what is deliberately excluded (prices, FAQ), which helps an agent avoid a wasted call. It stops short of describing return structure, but for a static read-only tool that gap is minor.

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 tight sentences: payload, intended use, and boundaries/alternative. The highest-value information (what it returns) is front-loaded and there is 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?

With no output schema and no parameters, the description carries the burden of telling the agent what comes back, and it does so by enumerating the payload components. Combined with the explicit exclusions and sibling pointer, an agent has everything needed to 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, so the schema-baseline of 4 applies and there is no parameter syntax for the description to compensate for. The description correctly spends no words on inputs.

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 (Returns) plus the exact resource and enumerates its payload: three phases, four capability pillars, positioning, recommended offer, Discord community. This is far more specific than the title alone and clearly distinguishes it from siblings like get_pricing or get_faq.

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 explicit when-to-use ("Use it to explain what the framework is"), explicit exclusions ("does not return prices or the FAQ"), and names the alternative with its triggering condition ("To check readiness, use assess_ai_readiness"). Nothing 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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds genuine value beyond them by clarifying 'It does not take payment' — important because the tool surfaces checkout links and an agent could otherwise assume it initiates a transaction. It stops short of describing freshness of pricing or any rate limits.

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 sentences, front-loaded with the core purpose, then routing, then the payment clarification. The enumeration of covered products is dense but each item carries selection value; nothing is redundant 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?

With no input parameters and no output schema, the description carries the burden of explaining what comes back, and it does so by naming the price categories, seat tiers, co-branding and Rollout Pack plus the checkout links. An agent knows both what it gets and what it must not expect (no payment action).

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 no parameter semantics to explain; this is the baseline case. The description correctly avoids inventing inputs and instead spends its words on what is returned.

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 ('Returns current one-time prices and checkout links') and enumerates exactly what is covered: Framework + Executive Suite, Framework alone, AI at Work seats, seat tiers, co-branding, and the Rollout Pack. It also explicitly distinguishes itself from get_seat_quote and assess_ai_readiness, so an agent can separate it from siblings 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 explicit routing: 'Use it for the full price list, or get_seat_quote for a specific number of seats,' and adds a second alternative for a different intent ('To check readiness, use assess_ai_readiness'). When-to-use and when-to-use-something-else are both stated, not implied.

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 the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavioral detail: it flags when a higher tier is cheaper in total, surfaces Executive Suite and Rollout Pack alternatives, and clarifies it does not place an order. This is output-level behavior an agent needs and cannot get from the 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?

Three tight sentences, front-loaded with the core calculation, followed by behavior and routing. Every clause carries information; 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?

With no output schema, the description compensates by describing what the tool produces (tier-cheaper flags, Executive Suite and Rollout Pack alternatives) and what it explicitly does not do. Nothing essential for correct invocation 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 100%, so both parameters (seats, coBranding) are already documented in the schema. The description restates the 1-500 range and co-branding but adds no syntax or defaulting detail beyond what the schema provides, making the baseline 3 appropriate.

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 ('Calculates the AI at Work cost') plus scope ('for a given number of seats (1-500)') and an optional modifier (co-branding). It is clearly distinguishable from siblings like get_pricing and assess_ai_readiness, which are named or implied.

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 states a when-not ('It does not take an order') and routes the agent to an alternative ('To check readiness, use assess_ai_readiness'). It doesn't explain when to prefer this over get_pricing, so it stops short of a full when/when-not/alternatives treatment.

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 safe read-only, idempotent, non-destructive profile, so the bar is met structurally. The description nonetheless adds a genuinely useful behavioral fact the annotations cannot convey: it informs but does not deliver the file, preventing an agent from trying to use it to send the kit. No mention of format/limits, but this is a static info tool.

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 tight sentences, each carrying distinct load: what the artifact is, when to use it, and two explicit routing/caveat rules. Front-loaded with the resource identity before the constraints.

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 parameterless informational tool with annotations covering the safety profile and no output schema to defer to, the description fully answers what it returns (a description of the kit and how to obtain it) and where to go instead.

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 0 params applies. Nothing added or missing on this dimension.

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 (Describes) and resource (the free AI Capability Briefing Kit, a 10-page internal briefing document), and explicitly names what it is not by routing to email_me_the_kit and assess_ai_readiness. An agent can distinguish this from all siblings 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?

Explicit when-to-use ("when the user wants a free starting resource") plus explicit exclusions and alternatives ("does not deliver the file; use email_me_the_kit when the user asks for it by email"). Routing conditions are fully specified.

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, closed-world behavior, so the safety profile is covered. The description adds a genuinely useful behavioral detail — returns excerpts, not full documents — which sets expectations about result granularity beyond the 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?

Three short sentences, front-loaded with purpose, then output-shape caveat, then routing. Every sentence earns its place and none restate structured fields.

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?

No output schema exists, and the description compensates by describing the return (excerpts plus source links). For a single-parameter search tool with full annotation coverage, nothing an agent needs to invoke it correctly 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 100% with a single well-documented 'query' parameter, so the schema carries the load. The description notes it accepts 'a phrase', which mildly reinforces the schema but adds no syntax or format detail. 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?

A specific verb (searches) plus the exact corpus it covers (methodology, definitions, positioning, changelog) and the return shape (matching sections with source links). This distinguishes it from get_faq and get_framework_overview without opening those schemas.

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 states the selection condition clearly — 'Use it for a concept the other tools do not cover' — and names a concrete alternative ('To check readiness, use assess_ai_readiness'). It stops short of enumerating which sibling tools already cover which topics, so the agent must infer the boundary.

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