OmniPost

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

Annotations declare readOnlyHint=true and openWorldHint=true, which already signals a non-mutating, external-calling tool. The description adds genuinely useful context beyond that: the x402 payment cost ($0.05 USDC hosted vs $0.01 BYOK), that the API key is used once and never stored, that violations are auto-repaired, and the 'Never invents facts' constraint. It does not describe latency, rate limits, or failure modes when validation cannot be repaired.

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 dense sentences with the price and payment model front-loaded, then the capability summary. Every clause carries information, though the parenthetical pricing details sit before the core purpose, which is slightly backwards for an agent scanning for 'what does this do'.

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 18 parameters, no output schema, and a paid two-path (hosted vs BYOK) flow, the description does a fair job: it names the return payload (hooks, Fit Scores, share intents) and explains the payment challenge handshake. The gap is that nine input parameters remain unexplained and there is no output schema to fall back on.

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 50%, so half the 18 parameters (cta, goal, link, avoid, brand, voice, audience, language, hasMedia) are undocumented in both schema and description. The description does add meaning for the BYOK path (api_key, provider, model map to the '$0.01 with your own provider key' tier) and confirms the up-to-14 platform default. That partially compensates but falls short of the majority-undocumented surface.

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: rewrites one post into native versions for up to 14 platforms, validates every variant, auto-repairs violations, and returns hooks, Fit Scores and share intents. That is far more than a tautology. It does not, however, explicitly contrast itself with the closely overlapping sibling omnipost_validate (which also validates variants), so sibling differentiation is only implicit.

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?

Pricing tiers and the instruction that omitting payment_signature yields the payment challenge give real usage context. But there is no statement of when to choose this over omnipost_validate, omnipost_publish, or omnipost_share_intents, so the routing decision is left to inference.

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 beyond the annotations by disclosing the cost model ($0.01 USDC via x402) and the return format (data URLs), and the schema explains the payment challenge flow when the signature is omitted. Missing details on output size/volume (14 variants returned at once) and any rate or payload limits keep 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?

Three short sentences with the paid precondition front-loaded and zero filler; every clause conveys new information (cost, transformation, ratios, return type).

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 five-parameter, nested-object tool with no output schema, the definition covers cost, transformation, ratios, and return type, and the schema fills in payment and input details. It stops short of describing the shape of the returned data-URL collection or behavior when only some platforms fail.

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 already 80%, so it clears the baseline, and the description adds real meaning by explaining that focus drives focal-point cropping rather than being an abstract x/y coordinate. It does not add anything about format conversion or the payment_signature semantics 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?

States a specific transformation (one image → every platform's exact ratio and pixel size) and enumerates the ratios produced (16:9, 4:5, 1:1, 9:16, 2:3, 4:3) plus the return form (data URLs). This is enough to distinguish it from omnipost_platform_specs (which presumably reports specs) 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?

Implies you call it when you need platform-ready image variants and notes it is a paid call, but names no alternatives or exclusions among the six siblings (e.g. when to prefer omnipost_validate or omnipost_platform_specs). Usage is inferable rather than stated.

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 the safety profile is covered. The description adds useful context that this is a free, x402 v2 payment-terms resource with current prices, but it does not disclose response shape, caching, rate limits, or auth requirements.

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?

The description is a single front-loaded sentence with no wasted language. 'FREE.' is terse but conveys material cost information, and the enumerated contents follow immediately.

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, read-only informational tool with no output schema, enumerating the returned concepts is nearly sufficient. Minor gaps remain around how the payment terms should be used or whether the data is static or dynamic beyond 'current prices.'

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?

This tool has zero parameters, so there are no parameter semantics for the description to compensate for. The empty input schema is compatible with a pure informational lookup, matching the baseline 4 for no-parameter tools.

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 resource, x402 v2 payment terms for OmniPost paid tools, and enumerates the fields it covers (network, USDC asset, payTo, facilitator, headers, current prices). It lacks an explicit verb and does not directly contrast itself with sibling tools, but the payment-domain purpose is clear.

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 'for OmniPost paid tools' implies this is relevant when an agent needs payment details before using paid capabilities. However, there is no explicit when-to-call guidance, no prerequisite statement, and no comparison to alternatives such as omnipost_publish or omnipost_validate.

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 adds value beyond that with "FREE" (cost signal) and "Verified" (provenance/currency of the limits), which materially affects whether an agent trusts the numbers. It doesn't mention caching or versioning of the specs, keeping it out of 5 territory.

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?

Three short sentences, no redundancy, with the cost note and scope front-loaded before the usage instruction. Every clause 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, the description compensates by enumerating the returned fields, so an agent knows what to expect from the call. For a zero-required-parameter, read-only lookup tool, nothing needed for correct invocation 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 description coverage is 100% and the sole parameter's description already states "Target platforms (default: all 14)". The description's "14 social platforms" reinforces but does not add semantics such as case sensitivity or behavior with an empty array, so the 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?

The description names a specific resource (per-platform specs) and enumerates exactly what is returned: character/title limits, hashtag caps, image ratios and pixel sizes, link behavior, publishing method, across 14 named platforms. That specificity lets an agent separate it from omnipost_validate (which checks content) and omnipost_publish (which posts) without opening a 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?

"Use before writing any social post" gives a clear triggering condition and sequencing advice. It stops short of naming an alternative or exclusion — e.g. it doesn't say to prefer omnipost_validate for checking already-drafted copy — so a 4 rather than a 5.

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 mutation semantics (readOnlyHint=false, openWorldHint=true), but the description adds genuinely non-derivable behavior: a per-call price of $0.01 USDC via x402, a hard cap of 20 targets, and the security-relevant guarantee that credentials are used once and never persisted. It stops short of describing failure/partial-success behavior, which matters for a multi-target publish.

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 no filler, and the cost/target-limit constraint is front-loaded before the capability list. The parenthetical auth details compress a lot into little space without becoming unreadable.

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 two-parameter, no-output-schema tool, the description covers cost model, target ceiling, supported destinations, credential handling, and the payment handshake, which is close to sufficient. The remaining gap is what a caller gets back across many targets (partial failures, per-target results), which an agent would reasonably want before invoking.

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 jobs parameter already spells out the per-target object shapes, so the schema is doing the heavy lifting. The description adds no further detail about the jobs array structure, target mix, or ordering, so the 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?

The description uses a specific verb ("Publishes") and enumerates the concrete destinations and auth mechanisms (Discord webhook, Telegram bot, Bluesky app password, generic webhook), so the agent knows exactly what the tool does. It does not, however, contrast itself with the sibling omnipost_fanout, which appears to be the closest alternative for multi-target delivery.

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: the pricing line and the "credentials used once and never stored" remark suggest this is the go-to direct-publish path, but there is no explicit when-to-use/when-not guidance and no routing to omnipost_fanout or omnipost_validate. The one actionable hint (omit payment_signature to receive the challenge) is largely duplicated by the schema.

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 adds real value beyond that by disclosing the cost ('FREE') and clarifying that output is share URLs / copy-and-open targets, not actual posts — but says nothing about auth needs or per-platform limitations.

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; the 'FREE' tag and verb come first. The long platform enumeration is verbose but earns its place by telling the agent exactly which networks are covered.

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 a nested-object parameter at 0% schema coverage and no output schema, the description needs to explain variant structure and return shape but does neither. Annotations cover the read-only safety profile, but an agent still cannot construct a valid call from this text.

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 0% with three parameters including a nested 'variants' object. The description only alludes to 'each variant' and never explains what key 'link' or 'mediaUrl' should hold or what shape a variant takes, so it fails to compensate for the undocumented 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+resource ('builds official one-tap share URLs') and enumerates the platforms covered plus the copy-and-open fallbacks. An agent can distinguish this URL-generation tool from omnipost_publish without opening the schema, though no sibling is named 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?

The description never states when to use this instead of omnipost_publish or omnipost_fanout, only what it produces. 'FREE' hints at cost-based selection but no explicit when/when-not guidance is given.

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, and the description is consistent with a pure read/analysis operation. It adds real value beyond the annotations: 'FREE' (no credit/quota cost), 'deterministic' (reproducible, not LLM-judged), the exact rule set checked, and the 0–100 score output. It omits whether it reports per-issue violations alongside the score, which would have made it 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?

A single front-loaded sentence that puts the cost signal first and the output value last, with no filler. The parenthetical check list is dense but each item earns its place by scoping what 'limits' means.

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?

No output schema exists, so the description does explain the return value (0–100 Fit Score per platform), but not the result shape — whether violations, reasons, or per-check pass/fail are included, which an agent needs to decide whether to show results to a user. The undocumented 'hasMedia' param and the nested variants structure remain unresolved.

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 only 50%: 'variants' carries a shape hint in the schema, but 'hasMedia' is documented nowhere. The description never mentions either parameter, nor how media presence changes which checks apply (e.g., image/hook rules). With a coverage gap and a nested object param, the description needed to compensate and does not.

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?

Specific verb + resource: deterministically checks platform-specific post variants against verified limits and returns a 0–100 Fit Score per platform. The enumeration of checks (X weighted count, IG hashtag cap, Telegram caption limit, dead links, hook-below-fold) makes it clearly distinct from siblings like omnipost_publish or omnipost_platform_specs.

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 leading 'FREE.' signals a cost-based reason to prefer this call, and 'validate variants' implies a pre-publish check, but the description never states when to run it (before publishing?) or how it relates to alternatives such as omnipost_platform_specs, which likely exposes the same limits. Usage is inferred rather than stated.

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