authority.md

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

With no annotations, the description carries the full burden and does disclose the return shape: metadata, a 'type' field, and a content preview. It also warns that bundle responses include the full list of persona slugs required by purchase_persona, a non-obvious cross-tool behavior. It omits error handling for invalid slugs and any auth/rate considerations.

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 core action, and the workflow and return-value notes follow logically. The slug examples are repeated verbatim from the schema, which is a small redundancy, but every other sentence earns its place.

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 or annotations, the description adequately covers what is returned and why (preview before purchase). Remaining gaps are minor edge cases such as invalid-slug behavior, which are not critical for a single-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% and the single 'slug' parameter is already documented with the same four slug examples. The description largely restates this rather than adding format or validation detail, 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 ('Get the full details for a specific product') and enumerates the four content types it covers (persona, Tool, Playbook, Bundle). It also differentiates from siblings by positioning itself after search_personas and before purchase_persona.

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 clear sequencing guidance ('Use after search_personas to show complete information before purchase') and names purchase_persona as the downstream action for bundles. It stops short of stating when this tool should not be used versus alternatives, but the workflow context is unambiguous.

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?

With no annotations, the description carries the burden. It states this is a listing operation that returns all categories from authority.md, implying a safe read with no side effects. It does not describe the output shape or ordering, but for a simple category list this 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 tight sentences, with the core action front-loaded and the usage guidance immediately after. No filler or repeated schema content.

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-parameter listing tool, the description gives enough context to choose and invoke it correctly. The only thing absent is an explicit statement of the return format (e.g., an array of category names), which is not critical for such a simple operation.

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?

There are no parameters, and the schema is an empty object with 100% coverage, so the baseline of 4 applies. There is nothing for the description to add.

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 ('List') and resource ('all categories of thinkers available on authority.md'), with concrete examples (Investor, Tech Visionary, Philosopher). It clearly distinguishes the tool from name-based search, its main sibling.

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 gives an explicit use condition: when the user wants to browse by domain rather than search by name. Though it does not name search_personas directly, 'search by name' unambiguously identifies the alternative path.

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?

With no annotations, the description carries the burden well: it discloses that it returns a URL to a Stripe-hosted checkout rather than processing payment itself, defines pricing models per item type, and enforces the user-confirmation requirement. It does not state auth requirements, whether a server-side order/session is created, or whether the URL expires, which keeps it short of 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?

Purpose is front-loaded and the Bundle mechanics and confirm-first rule follow in priority order. Every sentence is load-bearing, though the parenthetical bundle detail and the separate pricing sentence make it a touch denser than necessary for a one-parameter tool.

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 annotations, the description supplies the critical return-value context (a URL the user follows) and the pre-call confirmation workflow. Remaining gaps — URL lifetime, auth, and error behavior for invalid slugs — are modest for a URL-generating 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?

The schema documents only 'array of strings, 1-50 items'; the description adds real meaning — the valid entity types (personas, Tools, Playbooks), that mixed carts are allowed, and the non-obvious Bundle rule of passing all 10 persona slugs to hit the $29.99 tier. It stops short of describing slug format or how duplicates/unknown slugs are handled.

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 — 'Generate a checkout URL on authority.md for purchasing one or more frameworks, Tools, Playbooks, or Bundles' — which immediately separates it from the read-only siblings (get_persona_details, list_categories, search_personas). An agent can tell this is the terminal purchase step 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?

Explicitly states when to use it, how to buy a Bundle (pass all 10 persona slugs retrieved from get_persona_details), names a sibling for pricing lookups, and adds a hard precondition: 'Confirm with the user which items they want and the total cost BEFORE calling this tool.' Alternatives and exclusions are covered.

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?

No annotations are provided, so the description carries the burden. It usefully discloses the result shape ('type', slug, focus, price) and warns that current prices live at an external URL, which is real added context. However it says nothing about permissions, result limits/pagination behavior, or rate limits for a read tool that defaults to 10 and caps at 50.

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?

Purpose and scope are front-loaded in the first clause, and every sentence adds usable detail (product types, pricing, trigger conditions, result fields). It is dense and somewhat long, but not padded.

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 naming the returned fields ('type', slug, focus, price) and the pricing caveat. Given the sibling tools, it stops short of telling the agent when to escalate to get_persona_details or purchase_persona, which is the main 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 75% and the four product types are enumerated in the description, which enriches the meaning of the 'type' enum values well beyond the schema's terse gloss. The query, category, and limit parameters get no additional explanation, but the schema already documents them.

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 ('Search the authority.md marketplace') and describes the four product types it covers, which lets an agent distinguish broad search from a details lookup. It does not explicitly name its siblings (get_persona_details, list_categories), so differentiation is inferred rather than stated.

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 clear trigger conditions: 'Use when the user asks about a specific person, a category, a task they want help with, or wants recommendations.' This is solid context, but it names no alternatives or when-not-to-use cases (e.g. when to prefer get_persona_details or list_categories).

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