Agent Prompts A to Z

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description stays consistent with that by returning a link rather than performing a transaction. It adds useful context beyond the annotations: the return contents (URL plus price) and the explicit limit on agent authority to purchase. It doesn't mention failure modes for invalid slugs.

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 tightly written sentences with the payoff (URL and price) front-loaded and the constraint second. Every phrase 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?

For a single-parameter read tool with no output schema, the description covers what is returned (Payhip URL and price) and the agent's permitted role, which is enough 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?

With one parameter at 100% schema description coverage, including a concrete slug example, the schema already carries the semantics. The description adds nothing about slug format or handling of unknown slugs, so 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 Payhip URL and price — and scopes it to a paid pack or the bundle. That scope implicitly separates it from get_free_pack, but the sibling is never named, so the differentiation is inferential rather than explicit.

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 second sentence gives a clear behavioral constraint — the human completes checkout, don't purchase unless explicitly asked — which is a form of when-not guidance. However, it never says when to reach for this tool versus list_packs, recommend_pack, or get_free_pack, so selection guidance is only 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 read-only, non-open-world profile, so the description's added value is the content shape it exposes: system prompt, template, example, tips, FAQ. That tells the agent the response is a complete document rather than metadata, which is genuinely useful. It doesn't mention size, truncation, or error behavior for unknown slugs.

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 the primary action front-loaded and the prerequisite second. No filler, no repetition of the title.

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 burden of explaining what comes back, and it does so by enumerating the returned sections. Combined with annotations covering safety and the schema covering the single parameter, 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?

Schema coverage is 100% and the slug property already carries an example, so the schema does the heavy lifting. The description adds only provenance ('slugs come from list_packs'), which is helpful but minimal — 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 full raw Markdown ... of a free pack by slug.' The 'free pack' qualifier implicitly separates it from get_buy_link and get_pack-style siblings, though it never names the contrast 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?

'Slugs come from list_packs' gives the agent a concrete prerequisite workflow for obtaining the required argument, which is the main usage risk here. It stops short of stating when-not to use it, but the free-only scope is implied by the name and description.

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 and openWorldHint=false, so safety is covered; the description usefully adds the granularity of what comes back (one-line summaries, recommend-when guidance, prices, URLs). It does not say whether full pack contents are excluded, whether results are paginated, or how large the list typically is.

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 front-loaded sentence with no filler; the verb and resource lead and the return-value details follow. It is dense but every clause describes output the agent will actually receive.

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 adequately by naming the per-pack fields. Remaining gaps — tag filtering semantics, result ordering ("A to Z" is mentioned but not tied to params), and pagination — are minor for a read-only 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 coverage is 100%, so the baseline would be 3, but the description adds nothing: the tag filter (e.g. cursor, research, discord) is never mentioned, and "free and paid" only vaguely gestures at the access enum that the schema already documents. The one substantive detail an agent needs — that filtering is optional — is left entirely to 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?

Names a specific verb and resource ("List Agent Prompts A to Z packs") and enumerates what each entry contains: summaries, recommend-when guidance, prices, URLs. It implies the plural catalog view that separates it from get_free_pack/get_buy_link/recommend_pack, but never explicitly contrasts with those siblings.

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 only implied: an agent can infer this is the browsing/overview entry point, and "(free and paid)" hints that the access filter exists. There is no explicit when-to-use, no statement of when to prefer recommend_pack or get_free_pack instead, and no prerequisites.

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 and openWorldHint=false, yet the description still adds real behavior: the matching mechanism (keyword match over summaries and tags), the result cap (up to 3), the ordering rule (free packs first), and the per-result rationale. It omits empty-result handling and how strict the keyword match is, keeping it below 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?

Two sentences, no filler, and the most important information (what comes back and how it is ranked) is front-loaded. Every clause contributes either scope, count, mechanism, or ordering.

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 must carry return-value information, and it does: count cap, inclusion of why-they-match, and free-first ordering. It stops short of describing the fields of each returned pack or what a zero-match response looks like.

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 single parameter already says 'one or two sentences'. The description only slightly enriches this by revealing that matching is keyword-based, which hints that concrete task terms beat vague prose. Baseline 3 applies since the schema does the heavy lifting.

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 (recommend matching packs) plus the input basis (a short task description) and output shape (up to 3 matches with reasons). It is clearly distinguishable from list_packs/get_free_pack by its ranking behavior, though it never names a sibling to sharpen the contrast.

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 opening clause gives a concrete trigger condition: the user describes what they are trying to do and wants suggestions. It does not state exclusions (e.g., when the pack name is already known, call get_free_pack directly), so an agent must infer the boundary against siblings.

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