Promptcelerator

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 still adds real return-value context — the original prompt text, translation, blanks, model, video, and creator credit — plus the note that a language code causes the translated prompt to be included, which is behavior an agent cannot infer from annotations.

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 sentence, front-loaded with the core action and followed by the payload enumeration. It is dense but every clause carries information; the trailing list of returned fields is the only mildly heavy portion.

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 carries the return-value burden and does so by enumerating the fields an agent receives. Combined with annotations covering safety and the fully documented two-parameter schema, an agent has everything needed to call this 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 description coverage is 100%, and the description largely restates what the schema already says about 'id' (search result or page address) and 'language' (adds the translated prompt). It adds no format details, error behavior for a bad id, or id-validation guidance beyond the schema. Baseline 3 is appropriate.

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 and resource — 'Returns one prompt in full' — and names the two valid id sources ('an id given by search or the address of a prompt page'), which links it to the sibling 'search'. It is clear what the tool does despite the opaque name 'fetch', though it never explicitly contrasts itself with 'list_options' or states that it is a single-item retrieval vs. the list-oriented 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 context is stated: the id comes from a prior search result or from a prompt page URL, which tells an agent the expected call sequence. There are no exclusions or anti-patterns (e.g., when to use search instead of fetching by id), so it falls short of the top score.

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, destructiveHint=false and closed-world scope, so the safety profile is fully covered. The description adds the content scope of the listing, but says nothing about whether the list is static or dynamic, how large it is, or how the language parameter shapes the results — which matters because the schema says titles come back localized.

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 sentence, front-loaded with the verb and the payload, with zero filler. Slightly dense colon-list phrasing but no sentence is wasted.

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 parameterless read-only enumeration with full annotation coverage and a fully documented schema, the description names all three returned content types, which is the key thing an agent needs. Only the interaction between the language parameter and the returned labels is unaddressed.

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 is a single optional parameter (language) and schema description coverage is 100%, fully documenting codes, effects on titles/summaries/links and the 'en' default. The description adds nothing about it, which is acceptable at full coverage but is a missed opportunity to note that the listing itself is localized.

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 ('Lists') and enumerates the exact resource contents: video models, categories, and camera/light/style techniques. It also ties itself to the sibling 'search' by framing the output as 'what search can filter on', which makes its role distinguishable without naming fetch. It stops just short of a 5 because it never distinguishes itself from 'fetch'.

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 phrase 'what search can filter on' implies the intended workflow (call this to discover valid filter values before searching), but that inference is left to the agent. There is no explicit 'use this when...' instruction and no statement of when not to call it or what to do instead.

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?

Goes well past the read-only annotations: it discloses result ordering ('best first'), a relevance tier vocabulary (strong/possible/weak), the per-result payload (prompt, page, video, model, creator), and the truncation behavior that full text requires 'fetch'. That is exactly the behavioral context annotations cannot express.

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?

Four sentences, front-loaded with purpose, then input shape, then return shape, then the fetch hand-off. Every clause carries information about inputs, outputs, or routing; nothing is repeated from the name or 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?

For an 8-parameter, no-output-schema search tool, the description supplies what the structured fields cannot: the result ordering, the relevance label set, the fields per hit, and the language fallback. Nothing an agent needs to call or interpret results 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 baseline is 3; the description still adds value by framing 'query' as a plain-language subject/mood/style/shot description in any language and noting English yields the closest matches — a nuance absent from the schema text.

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 ('Searches a free library of AI video prompts') and adds a distinguishing property ('each published next to the video it produced'). It also separates itself from the 'fetch' sibling by saying the full prompt text comes from there, so an agent can route without opening schemas.

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 when-to-use context: natural-language description of subject/mood/style/shot, English for closest matches, and explicitly delegates full prompt text to 'fetch'. It never names the 'list_options' sibling (only the schema does, for slugs), and gives no explicit exclusion beyond the fetch split.

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