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

With no annotations provided, the description carries the full burden and does meaningful work: it discloses that figures are never averaged across differing definitions, that DEFINITIONS_DIFFER is flagged, and that combined figures appear only under identical definitions. Missing are auth/rate-limit/permission notes and default-scope behavior, so not quite 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?

One tight sentence that front-loads the read-only nature and the normalization rule, with zero filler. The unexplained 'D0' prefix and dense clause stacking cost it a point.

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 read-only tool with no output schema, the description does well explaining result semantics (provenance, definition flags, non-averaging). However, it leaves the sole input parameter wholly undocumented and gives no guidance on default scope, which is a real gap for an agent trying to invoke 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?

There is one parameter (`platforms`, an untyped array) with 0% schema description coverage, and the description never mentions it at all — no format, no accepted values, no default-when-absent semantics. The description therefore adds nothing to a completely bare schema field.

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 the resource (unified analytics), its scope (per-platform figures normalized by metric key), and its operation (read-only report), which is clearly distinct from the sibling draft/syndication/receipt tools. It is specific but never uses a plain verb like 'returns' or 'generates', and the 'D0' label is unexplained jargon.

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?

'(read-only)' signals it is a safe read, which is useful context. But there is no statement of when an agent should call this versus the sibling tools, no prerequisites, and no indication of what happens when the optional `platforms` filter is omitted.

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?

With no annotations, the description carries real weight and delivers: it discloses the return value (an approval token bound to the content hash) and a non-obvious side effect (any later edit invalidates the token). It leaves out idempotency and failure behavior, but the invalidation rule is exactly the kind of trait annotations would otherwise cover.

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 tight sentences with no filler; the core action comes first and the token/invalidation caveat follows. Every sentence 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?

No output schema exists, and the description does explain the return value and its invalidation semantics, which is the main thing an agent needs. What remains thin is the parameter-level guidance and repeat-call behavior, both of which matter given two undocumented inputs.

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% and neither parameter is documented. The phrase 'owner approval' loosely hints that approved_by identifies the approver, but the description never mentions draft_id, never says whether approved_by is optional, and never clarifies whose identity or which version is targeted.

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 object: recording owner approval of the current draft version, which is clearly distinct from draft_create, draft_preview and syndicate_drafts. It stops short of explicitly naming siblings, but the action 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?

Usage is only implied: you call it to approve the current version, and the invalidation note hints at sequencing (approve after edits). There is no explicit when-not guidance, no mention of required owner privileges, and no statement about what happens if approval is repeated.

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?

With no annotations, the description carries the full burden and does real work: it discloses hash-binding semantics, that content_hash is the value approval binds to, and that re-creating an existing draft_id creates a new version and resets approval to none. It omits auth/permission requirements and failure modes (e.g. what happens on invalid variants), which keeps it short of 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 dense sentences, front-loaded with what is created and followed by the behavior that matters most (hash binding, versioning side effect). No filler, though the telegraphic '(home)' parenthetical is slightly cryptic rather than explanatory.

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, and the description does say a content_hash is returned, which covers the key return value. However, for a mutation tool with 8 parameters, a nested variants object, and zero annotation coverage, it leaves the variants payload shape, validation behavior, and permission requirements unexplained.

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 0% across 8 parameters, so the description must supply the missing semantics. It mostly just re-lists the parameter names (title, body, subtitle, tags, audience) with only two hints of meaning — 'canonical_url (home)' and 'per-platform variants' — and gives no structure for the nested variants object or the draft_id format.

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 (create/re-version) and resource (the canonical draft) and enumerates the content it covers. The '(or re-version)' clause and the draft_id note separate it from a pure create, though it never names draft_preview, draft_approve, or syndicate_drafts to draw the workflow boundary 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 note that re-creating an existing draft_id makes a new version and resets approval implies the intended entry point of the draft→approve→syndicate flow, but it never says to use this instead of draft_preview or draft_approve, nor when not to call it. Usage must be inferred from the sibling names.

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?

No annotations exist, so the description carries the full burden. It does disclose genuine domain behavior by explaining per-platform constraints (Substack = paste pack, beehiiv = draft-only), which is useful context beyond the name. It says nothing about whether the call is read-only, whether it triggers rendering work, or about cost/latency, leaving meaningful gaps for an unannotated tool.

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 dense sentence with no filler, and the core payoff (per-platform previews plus diffs) is front-loaded. The parenthetical about platform constraints is worth its length, though the jargon ('adaptation diff', 'paste pack') is left undefined.

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 one-parameter read tool with no output schema, the description does sketch the return payload (rendered previews and diffs), which the schema cannot. It stops short of describing structure, size, or how many platforms appear, so an agent still cannot anticipate the response shape.

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 0% and the single parameter draft_id appears nowhere in the description. The argument is largely self-explanatory from its name, but nothing explains whether it accepts an ID versus a slug, or what happens with an unknown or unapproved draft.

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 the specific artifact produced: per-platform rendered previews plus adaptation diffs against the canonical draft. That distinguishes it clearly from draft_create, draft_approve, and syndicate_drafts. It never states the operation as a verb (fetch/generate), reading more like a description of output than an action, which keeps it from 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?

'The review artifact' faintly implies use at the review stage, but there is no explicit when-to-use, no prerequisite such as an existing draft_id, and no comparison to draft_approve or syndicate_drafts. An agent must infer the call site from the noun phrase alone.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that receipts are hash-chained and that the tool can verify the chain, which is behavior beyond the schema. However, it does not state whether the operation is read-only, what permissions are required, pagination/order behavior, or what happens when verification fails.

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 words, and the parenthetical enumeration earns its place by clarifying receipt categories. It slightly conflates two behaviors, listing and chain verification, without clarifying whether verification is always performed, which keeps it from a 5.

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 read-only listing tool with no output schema, the description identifies what is listed and notes chain verification, which is adequate to start. It still omits return structure, limit behavior, default ordering, and failure semantics for chain verification, so an agent lacks some context needed to invoke it confidently.

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 only parameter, "limit", has 0% schema description coverage, and the description does not mention it at all. It adds no semantics such as default value, maximum, or whether the limit applies before or after chain verification, though the single optional and intuitively named parameter keeps this from being a 1.

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 gives a specific read verb ("List") and resource ("hash-chained receipts"), then enumerates receipt categories such as draft creations, approvals, syndications, and analytics runs. It does not explicitly differentiate itself from the sibling action tools, but the resource and read operation are clear enough that an agent can distinguish it.

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 enumerated receipt types imply an audit/history use case, but there is no explicit guidance on when to use this tool versus siblings, nor any exclusions or prerequisites. The mention of verifying the chain hints at a purpose but does not route the agent between alternatives.

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?

With no annotations, the description carries the full load and does well: it discloses the adapter targets, that Substack is a read-only paste pack and 'never a write', and that a valid approval hash is required. It omits what happens on an invalidated hash, whether re-running is idempotent or overwrites existing platform drafts, and any permission model.

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-loaded with the core action, then the fixture-adapter detail, then the hard constraint. Every clause carries information, though the parenthetical adapter aside is dense enough to slow parsing.

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 mutation tool with no annotations and no output schema, the description covers behavior and preconditions but leaves the platforms parameter, draft_id semantics, failure modes, and return shape undefined. An agent knows roughly what the tool does but not exactly what to pass or expect back.

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 0% across three parameters, so the description must compensate and largely does not: only approval_token is explained (approval hash requirement). draft_id and especially platforms (an untyped array — which platform identifiers are valid, whether omission means all platforms) get no meaning from either schema or description.

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 (fan out / syndicate) and resource (approved draft → per-platform drafts) and scopes it with 'there is no publish path'. It implicitly distinguishes itself from draft_create by requiring an already-approved draft, though it never names the sibling 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?

Gives clear preconditions — requires the approval token and an un-invalidated approval hash — and an explicit exclusion ('There is no publish path'), which tells an agent not to look here for publishing. It does not name which sibling to use instead when approval is missing.

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