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

Adds substantial behavioral context beyond annotations: the draft registry is in-memory (lost on restart), returns a draftId and validation report, and that post/schedule tools will reject undrafted posts with an error naming the exact text. This clarifies statefulness, side effects, and error behavior, consistent with the non-read-only, non-idempotent 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?

Two dense but well-structured sentences: the first front-loads the core action and registry behavior, the second covers the downstream rejection consequence. Every sentence adds necessary information with no filler or redundancy.

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 stateful draft tool with no output schema, the description adequately covers registry lifetime, return values (draftId and validation report), and downstream error behavior. It does not elaborate on what the validation report contains or the specific validation rules, but that is a minor gap given the sibling validate_thread likely handles validation details.

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 schema already documents the only parameter 'posts' including ordering and convention about links on the final post. The description adds no parameter-specific details beyond what the schema provides, so the baseline score of 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?

Starts with 'Validate a thread AND register the validated posts in the in-memory draft registry', a specific verb and resource that clearly distinguishes this tool from validate_thread (which presumably only validates) and from post_thread/schedule_thread (which reject undrafted posts). The mention of sibling rejection further clarifies its unique role.

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?

Explicitly states that post_thread/schedule_thread reject any posts array that was never drafted, implying this tool must be used before those. It also notes the draft is lost on restart and must be re-drafted before finalizing. However, it does not explicitly contrast with validate_thread (e.g., when to prefer one over the other), leaving a minor gap in alternative guidance.

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?

Beyond the annotations, it discloses the validation refusal, the pre-flight kill-rule threshold (score < 45), that the call only records an audit line, and that the real platform POST happens outside this server because it holds no X credentials. That is exactly the context an agent needs before invoking a non-idempotent, non-destructive write.

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 dense sentences, front-loaded with the core action and the prerequisite before the operational caveats. Slightly heavy with parentheticals ('verbatim sibling rule', 'score < 45 -> refusal'), but every clause carries 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?

Given no output schema, the description covers what the call actually returns conceptually (an audit line rather than a posted thread), the prerequisite chain, the refusal gate, and the credential boundary. An agent has everything needed to call it correctly and to interpret the result.

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?

With 50% schema coverage and a nested preflight object, the description adds real meaning, clarifying that the posts must be the exact validated text and framing preflight as an optional gate whose score < 45 causes refusal. It does not explain the posts ordering/link convention beyond what the schema comment already says, so it is additive but not exhaustive.

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 precise verb and object ('mark a VALIDATED draft as cleared to post NOW') and explicitly distinguishes itself from draft_thread, which produced the text. An agent can tell instantly that this is the publish-approval step, not the drafting or scheduling step.

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?

It gives a hard prerequisite ('requires the exact posts to have been drafted with draft_thread first') and a refusal condition for unvalidated text. It implies immediate posting vs the schedule_thread sibling ('post NOW') but never names that alternative explicitly, leaving a small routing gap.

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 beyond the annotations: discloses the draft-registry validation gate, the score < 45 kill-rule refusal that schedules nothing, and that state is in-memory and lost on restart. The 'workflow discipline, not a scheduler daemon' line usefully corrects a likely agent misconception about durability.

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 tight sentences, front-loaded with the core action, then preconditions, failure mode, and persistence caveat in order of decision relevance. No filler.

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?

Covers preconditions, failure modes, persistence semantics, and the nested preflight object's effect, which is the hardest part of the schema. With no output schema, the one remaining gap is what a successful response looks like, which is minor.

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 67%, and the description adds meaning the schema lacks: the preflight threshold behavior (score < 45 refusal), and that posts must be the exact drafted strings. run_at is restated as ISO-8601 UTC, which is redundant with the schema description but harmless.

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 (schedule) plus resource (validated draft thread) and a concrete timing semantic (ISO-8601 UTC run time). Clearly distinguishable from draft_thread, validate_thread, and post_thread by the scheduling framing.

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?

Explicitly states the precondition that posts must come from draft_thread and that the registry rejects unvalidated text. It does not explicitly say 'use post_thread instead for immediate publishing', so the alternative routing is only implied rather than named.

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 readOnly/idempotent/non-destructive, and the description reinforces that with an explicit 'Side effect: none' plus the registry acceptance rule, which is real added context. It also discloses the return shape (flags plus an issue list with per-post evidence) and the specific rule set applied, though it doesn't say how severe flags are surfaced or whether validation is partial on failure.

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-loads the most decision-relevant fact (no saving) and packs the rule list into one dense sentence with no filler. Slightly run-on, but every clause carries information an agent would otherwise have to discover by calling it.

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?

Single-parameter, non-destructive tool with no output schema, and the description covers the checks performed, that nothing is persisted, and the rough return contents — enough to call it correctly. It stops short of describing the flag vocabulary or how issues map to posts, which is a minor gap given no output schema exists.

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% and the posts description already covers ordering and the links-on-final-post convention, so the baseline is 3. The description adds meaning the schema lacks — the 280-char per-post limit and that 'post 1' is evaluated specifically for hook quality — which clarifies what the parameter is judged against.

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 ('run the per-post evidence check on a draft thread') and enumerates exactly what is checked: 280-char limit, 25-post limit, empty posts, hook quality, links-on-final-post. It explicitly separates itself from draft_thread by declaring it saves nothing, so an agent can distinguish it from draft_thread/post_thread 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?

'WITHOUT saving anything' plus 'the registry only accepts drafts made with draft_thread' tells the agent this is a pre-flight check against a draft, not a creation or publishing step. It gives clear context but never explicitly names when to prefer post_thread or schedule_thread over this, or states a required call order beyond the registry caveat.

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