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

Annotations (readOnlyHint=false, openWorldHint=true, idemPotentHint=false, destructiveFint=false) already communicate mutation and open-world behavior, yet the description goes far beyond them: it reveals that the tool performs srprkly's own quota, duplicate-content, and platform pre-flight checks; that it reads the real bytes of media and reports the actual published outcome; that it can answer with a needsAccountChoice sentinel instead of scheduling when profile_ids is omitted; and that refusal messages list allowed values for bad privacyLevels, with 're-export instructions' for unsupported media formats. No annotation contradiction found and the behavioral disclosure is unusually rich for this tool-complexity.

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?

This is a very long description for a very large parameter surface (11 parameters, nested platform_metas objects, no required fields). It is trielsectionally front-loaded: the one-paragraph, your-priority sentence 'Queue a post for publishing, in ONECALL' then ordering by the intrinsic rule statements: industry/media strategies, checks, then platform requirements, then user-confirmation, then the needs-recall case. A few redundancies exist (the same 'required except YouTube/TikTok' and the Instagram/TikTok media-at-submission rule are said in both the top-level description and schema param text), but nothing is padded.

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?

This is a high-complexity tool (11 params, 0 required, 5 platforms, nested platform_meta, no output schema), and description copes with the absence of an output schema by explaining the exceptional result itself: it manifests what actual form each platform will publish, whether media_urls are picked up as a trick, and especially the needsAccountChoice path that instructs the agent to put the option to the user and re-call. It protects against bad calls by telling the agent to confirm date/time/target accounts and to respect user-given title and privacyLevel. There is no next-necessary information about scheduling this non-obvious branch is meaningfully disclosed.

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 schema already documents 100% of the parameters in detail, so the baseline is 3. This description adds genuine strategy on top: it tells the agent to prefer a user-supplied link over media_ids and explains why storage/upload is a pre-ocrateme, it instructs that a reqUrl for a Google Drive/Dropbox link be converted automatically to sidestep, that th e allowed media formats are JPEG/PNG/WePB/GIF/MP4/MOV/WeBM, and that the presentation rules require asking the user face-firstiTime vs i-Story on Instagram, otherwise It would fall on a simple lists—which is precisely what adds decision guidance the parameters alone do not convey explicitly.

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?

Opens with a specific verb-resource pair and the key differentiator: 'Queue a post for publishing, in ONE call.' The 'in ONE call' phrasing immediately separates it from multi-step publish flows, and the body makes it clear this is the final scheduling action, not a draft, a validation, or a deletion. A reader can distinguish it from siblings like sprkly_draft_post, sprkly_validate_post_policy, and sprkly_delete_scheduled_post 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 concrete when-to-use routing: pass the user's link straight to media_urls instead of running an upload tool; use media_ids when media is already in sprkly or reused across posts; never let the tool guess a Story vs Reel; pass an explicit time instead of relying on auto-publishing, and use sprkly_get_analytics to suggest one; fetch allowed TikTok privacy levels via sprkly_get_tiktok_posting_options. This is strongly actionable. It does not explicitly say 'use draft_post instead for pre-publish planning' or 'use validate_post_policy for a non-committal check,' but the guidance that exists leaves little ambiguity about when this tool fires.

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