369 Meter — pay-per-call APIs for agents (x402)

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the description's real contribution is the payment mechanism: $0.03 USDC on Base via x402 against POST /v1/game/facts. That is material behavioral context an agent needs to avoid unexpected cost. It does not state what happens on payment failure or rate limits, 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, zero filler. The usage trigger is front-loaded and the pricing/endpoint detail follows in a compact second sentence.

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 usefully enumerates the expected return fields, and it discloses cost and transport. It is slightly thin on response shape (e.g., ranking or no-match behavior) for an open-world lookup tool, but the essentials for correct invocation are present.

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%, with 'query' documented as the game title and 'limit' bounded 1-5 with default 3, so the schema carries the semantics. The description adds only the implicit notion of a title lookup and nothing about match ambiguity or how limit affects results. 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 names a specific verb+resource ('live game metadata from RAWG') and enumerates the returned data fields (release date, ratings, Metacritic, platforms, genres). An agent can immediately tell this is a title-lookup tool and distinguish it from the unrelated siblings (hook_score, text_analyze, translate_check).

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?

'Use this when you need live game metadata from RAWG' gives an explicit triggering condition, and the pay-per-call pricing tells the agent a decision-relevant constraint before invoking. It stops short of naming when *not* to use it or any alternative source, but the sibling set makes alternatives unnecessary.

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 destructiveHint=false, so the description correctly adds the non-obvious behavioral fact: this is a paid call at $0.01 USDC on Base via x402 at POST /v1/hook/score. Cost and payment rail are exactly the kind of context annotations can't carry; it doesn't cover latency or failure/refund behavior.

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 with zero filler: the usage condition is front-loaded and the payment mechanics follow. Nothing is repeated from the name or schema.

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 simple 2-param scoring tool with a 0-100 output range stated in the description and safety covered by annotations, an agent has what it needs to call it. The only gap is what the score response actually contains beyond the number, though no output schema exists to cover 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?

Schema description coverage is 100%, so both parameters (headline, platform) are already documented, establishing the baseline 3. The description adds no meaning about parameter defaults or valid platform values 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?

States a specific verb and resource ('scored 0-100') plus the scoring rubric ('369 team's hook rules'), and limits scope to gaming headlines, which cleanly separates it from siblings like game_facts or text_analyze.

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?

'Use this when you need a gaming headline or hook scored' gives a clear triggering condition. It doesn't name alternatives or state when not to use it, but the niche is narrow enough that little inference is required.

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 establish read-only, closed-world, non-destructive behavior, so the description correctly doesn't repeat that. It adds the crucial non-obvious traits: a paid call ($0.01 USDC on Base via x402) and the REST route POST /v1/text/analyze. It doesn't cover failure modes (e.g., insufficient payment, oversized text beyond the schema note), keeping it from 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, zero filler, front-loaded with the use condition followed by the payment and routing details. Every clause carries information an agent needs.

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-param read-only tool with no output schema, the description covers the trigger condition, the analysis dimensions returned, the input constraint (via schema), and the payment/transport requirements. It's only slightly short of complete because it doesn't describe the response shape precisely or error behavior on payment failure.

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 parameter with 100% schema description coverage including the 20000-char limit, so the baseline is 4. The description adds no additional parameter meaning beyond what the schema already states.

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 a specific verb and resource ('deterministic text analysis') and enumerates the concrete outputs (counts, Flesch readability, script mix, top keywords), so an agent knows exactly what it gets back. It doesn't explicitly distinguish itself from siblings like hook_score, which could plausibly overlap on text scoring, so it falls short of a 5.

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?

'Use this when you need deterministic text analysis' gives a clear selection condition, and the enumerated outputs sharpen that context. It names no alternatives or exclusions, so there's no guidance on when to prefer hook_score or translate_check 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?

Annotations already cover the safety profile (readOnly, non-destructive, closed-world). The description adds materially important behavior the annotations don't: a $0.02 USDC charge on Base via x402 and the underlying REST route POST /v1/translate/check. It doesn't describe failure modes or what happens if payment is declined, 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, both dense in information: the first front-loads the use case and output, the second carries cost and transport. No filler, and the most decision-relevant content comes first.

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 2-parameter scoring tool with no output schema, the description covers purpose, evaluation dimensions, the 0-100 return range, and the payment/transport model an agent must know before calling. A brief note on response shape beyond the score would make it fully complete.

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 both parameters are already documented, and the baseline is 3. The description adds the evaluation criteria the two texts are judged against, which gives useful context, but it doesn't clarify parameter-level semantics (e.g., direction detection, length limits) beyond what the schema states.

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 names a specific verb+resource (EN<->FA translation QA score, 0-100) and enumerates the criteria checked: numbers/entities preserved, script purity, untranslated segments. It does not differentiate itself from siblings like text_analyze or hook_score, but the tool's identity is unambiguous.

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?

"Use this when you need an EN<->FA translation QA score" gives an explicit trigger condition. It doesn't name when NOT to use it or point to a sibling alternative such as text_analyze for general text checks, so it stops short of full routing guidance.

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