AI Setups That Work

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 valuable return-content detail (what fields the setup includes and the tested/researched label) that annotations cannot convey.

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?

One compact sentence that front-loads the core action and then lists the payload contents; every clause adds 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?

Simple read tool with complete annotations and full parameter documentation. With no output schema, the description correctly compensates by enumerating returned fields, leaving nothing essential unknown to a caller.

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, so baseline is 4. The description adds provenance context by tying the slug to search_setups, which is genuine meaning beyond the schema's bare 'The setup slug.'

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?

Specific verb+resource ('the full setup for a slug') with an enumeration of exactly what the record contains: audience, steps, prompt, snags, sources, and label. It is clearly distinct from search_setups, which only discovers slugs.

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?

Phrasing 'a slug from search_setups' implicitly routes the agent: search first, then fetch by slug. It gives clear context for when to reach for this tool but doesn't state exclusions or contrast explicitly with get_skill.

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 adds value beyond that by disclosing the return shape (file content plus zip link) and the failure/empty condition, though it stops short of saying how a missing skill is signaled (error vs. empty).

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 short sentences with no waste; the deliverable and file path are front-loaded, and the caveat lands last where it is easy to catch. The opening noun-fragment phrasing is slightly clipped but costs nothing in practice.

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, so the description must carry return-value burden — and it does, naming both artifacts returned and their intended use. The one gap is how the "no skill" case manifests at call time, which an agent would want to know before invoking.

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?

With one parameter at 100% schema coverage, the schema already documents `slug` as "The setup slug." The description reinforces that the slug identifies a setup and that only skill-bearing setups resolve, but adds no format or resolution detail beyond the schema — baseline 3.

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 precisely what is returned: the SKILL.md content for a setup, a ready-to-save file path, and a .zip link for the Claude app. It is clear enough to distinguish from get_setup, which returns the setup itself, though it never names the sibling explicitly.

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?

"Only setups with a skill have one" tells the agent the precondition for a successful call, which is genuinely useful. However, there is no explicit guidance on when to call get_skill versus get_setup, nor what to do when the setup lacks a skill — the agent must infer both.

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 this as a read-only, idempotent, non-destructive search. The description adds useful behavior beyond annotations: results are ranked with Tested setups first and include page links.

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, front-loaded with purpose and supported by concrete examples. Every sentence adds value without repetition or 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 search tool with fully described parameters and safety annotations, the description covers purpose, search context, result ranking, and returned links. 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 all five parameters are already documented. The description reinforces the query purpose with examples but adds no parameter-specific semantics 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 a specific verb and resource ('Find AI setups') and gives concrete job examples such as chasing late invoices. It clearly describes discovery-style search, but does not explicitly distinguish this from sibling tools like get_setup.

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 examples make the intended usage clear: search by job or problem when looking for relevant AI setups. It lacks explicit exclusions or a direct comparison to get_setup, but the context is sufficiently clear.

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