Just Fucking Prompt It

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

Adds real context the annotations cannot convey: every question is screened and offensive ones are refused, the response contains a link plus a tone-appropriate line, and the link must be passed through verbatim. Annotations already declare the non-read-only, open-world, non-idempotent profile, and the description does not contradict them. Minor gap: it does not say whether repeat calls produce identical or distinct links, which matters against idempotentHint=false.

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 definition, then usage rules, then inputs, then return behavior – a sensible order with no filler sentences. Slightly long for a two-parameter tool, but each paragraph carries distinct information.

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?

An output schema exists, yet the description still gives the one agent-actionable fact the schema can't: the returned link must be delivered exactly as received, alongside the supplied line. Combined with the moderation-refusal caveat and the usage guardrails, 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?

Schema coverage is 100%, so the schema already carries the 500-character limit, the required question field, and the mild/rude/brutal enum with default mild; the description largely restates these. It adds only the framing that 'question' is the other person's wording and that 'tone' shapes the answer style, which is modest value over a fully documented 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?

States a specific verb and resource ('Creates a ... JFPI link') and then explains what the artifact actually is: a joke site where a recipient watches their question being typed into an AI. An agent knows exactly what this tool produces 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?

Gives explicit positive triggers ('only when the user asks for a JFPI or "just prompt it" link for someone else') and explicit exclusions ('Do not use it on your own initiative, and never use it to mock the user you are talking to'). This is the highest-risk ambiguity for a joke tool and it is closed off directly.

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, non-destructive, and a closed world, so the safety profile is covered. The description adds value beyond that by disclosing the exact enumerated tone values and the shape of each entry (one-line description plus an example opener), letting the agent reason about output before calling. It does not add rate-limit, caching, or ordering context, so not 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, both earning their place: the first states what is returned and its shape, the second states when to call it. Front-loaded with the resource before the usage trigger.

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?

A parameterless, read-only lookup with an output schema and full annotation coverage needs very little prose. The description supplies the enumeration and entry shape, and the output schema handles return formatting, leaving no material gap for an agent deciding whether to call it.

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, and the description correctly avoids inventing filter or pagination concepts.

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 ('Lists the tones a JFPI link can have') and enumerates the actual values (mild, rude, brutal), plus what each entry contains. An agent can instantly distinguish this from the sibling create_jfpi_link, which writes rather than enumerates.

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 an explicit usage trigger: 'Use it when the user wants to choose how rude the link should be.' That clearly positions it as a pre-creation discovery step. It stops short of naming create_jfpi_link as the follow-up action or stating when not to call it, so it falls short of a 5.

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