Agentic Design School

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

Beyond the readOnly/idempotent annotations it adds real behavioral facts: the optional email is ignored, the response for a given slug is invariant to other arguments, purchases are one-time, and pricing is USD inclusive of GST for Australian buyers. These are exactly the details an agent would otherwise guess wrong about.

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 core behavior and the negative disclaimers are front-loaded and useful, but the trailing pricing sentences ('Fundamentals is free with an account... three leadership courses are US$300 once, sold together') are catalogue copy that belongs in get_course/list_courses rather than in this tool's definition.

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-required-parameter read-only tool with no output schema, the description covers the essential behavior, ignored input, and determinism. It is slightly ambiguous about the literal return shape — a URL string versus page content — and says nothing about how it relates to get_course.

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 are already documented, including that email is ignored. The description only reinforces that the slug maps into the returned URL path and adds no new format or validation 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?

The description gives a concrete verb+resource ('Return the public course page at https://agenticdesign.school/courses/<slug>') and explicitly disclaims what the misleading name suggests (no checkout session, no Stripe customer, no account lookup). It never names the siblings get_course or list_courses, so the boundary between 'course page URL' and 'course data' is left implicit.

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 supplies the selection context — 'where the buyer completes the purchase' — and a strong set of exclusions that stop an agent from using it as a checkout/session creator. There is no explicit 'use get_course for details instead' routing, so alternative selection is still inferred.

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 the description adds real context beyond them: lesson slides are excluded from the response, Australian prices include GST, Fundamentals is free, and leadership courses share a US$300 group price. It repeats 'this tool only reads' (redundant but consistent) and says nothing about error behavior for an unknown slug.

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?

Return contents are front-loaded in the first sentence, followed by scoping caveats and pricing rules. The pricing sentences are terse and slightly telegraphic ('Each leadership course is part of the US$300 group'), but each carries information an agent would otherwise get wrong.

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 usefully enumerates the returned shape and flags exclusions and pricing semantics. The only gap is failure behavior for a bad slug, which is minor for a simple 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 coverage is 100% for the single slug parameter, including the format example, so the schema already carries parameter meaning. The description only restates that it takes one slug; 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 ('Return the public outline and offer for one course slug') and enumerates the returned fields (audience, outcomes, modules, price), which cleanly separates it from list_courses (many courses) and create_checkout_link (purchase). An agent can pick it without opening the 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?

Usage is implied by 'one course slug' and the schema note that the slug comes from list_courses, but the description never explicitly says to call list_courses first or that this tool is the wrong choice for browsing. No exclusions or prerequisites are stated in the description itself.

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, idempotentHint=true and destructiveHint=false, so the closing "This tool only reads" is largely redundant. The description does add real behavioral context beyond the annotations: prices are one-time, GST-inclusive for Australian customers, paid designer prices come from a cached catalogue, and a live-price failure degrades to a "see the course page" placeholder rather than an error.

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 return fields are front-loaded in the first sentence and the pricing caveats follow in a logical order (currency, GST, cache source, fallback). Dense but each sentence carries distinct information, with only the "only reads" line being expendable.

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 full burden of describing return values, and it does so field-by-field plus explains the degraded-price fallback. For a zero-parameter read-only listing tool, an agent has everything needed to call it and interpret the result.

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 a parameterless tool applies. The description uses that space instead to explain the shape and provenance of the returned data.

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+resource ("List every Agentic Design School course") and enumerates the returned fields, so the agent knows exactly what it retrieves. It does not explicitly name the alternatives (get_course for a single course, create_checkout_link for purchasing), so sibling differentiation is only implied by the word "every".

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: an agent can infer this is the catalogue-browsing tool and that get_course is for a single item, but the description never says when to prefer this over get_course or create_checkout_link. No prerequisites or exclusions are given.

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