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

With no annotations at all, the description carries the full burden, and it does disclose the substantive payload: connection state, token expiry, publishing quota, and scheduler status. However, it never states that the call is read-only / side-effect free, nor what happens when no account is connected or the token has expired — gaps that matter for a status tool with zero annotation coverage.

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 compact clause with no filler; each listed item (token expiry, quota, scheduler status) is distinct information. It loses a point only because the telegraphic, verb-less phrasing makes it less immediately parseable than a front-loaded action sentence would be.

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 tool with no output schema, the description does reasonably well by enumerating the returned fields in place of a schema. It stops short of covering the failure modes (not connected, expired token) that an agent would want to know before calling, so it is adequate but not 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly implies the tool is parameterless and self-scoped to the connected account.

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 is a noun phrase naming the resource and the data it exposes (account, token expiry, 24h quota, scheduler status), but supplies no verb, so it reads as a label rather than a statement of what the tool does. The resource is identifiable and distinguishable from siblings like ig_publish or ig_insights, but only by inference.

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?

There is no guidance on when to call this versus ig_insights, ig_queue_list, or the other sibling tools, and no mention of preconditions such as whether the account must be connected first. The agent must infer usage entirely from the tool name.

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 it does disclose the output shape (errors, auto-fixable issues, warnings). However, it never clarifies that validation is read-only and does not itself apply fixes, nor what permissions or file-access constraints apply.

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 tightly packed sentence with the action front-loaded and the return contents appended. 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 two-parameter tool with no annotations and no output schema, the description covers purpose, target formats, and an overview of what comes back. The only gap is the absence of any statement that it is non-destructive and read-only.

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%, so the description must compensate. It effectively documents both parameters: 'local media file' clarifies that `path` is a local filesystem path, and the parenthetical list (reel/story/feed/carousel/cover) enumerates the `as` values, matching the schema enum exactly.

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 ('Validate') plus resource ('local media file') and the target spec domain (Instagram). It enumerates the five target formats, so an agent knows exactly what kind of check this performs, though it doesn't explicitly contrast with any sibling.

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 purpose implies usage (pre-publish validation), but nothing states when to call it versus, say, jumping straight to ig_publish, nor any prerequisites such as the file needing to exist locally. No exclusions or alternatives are 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?

No annotations are provided, so the description carries the full burden. It adds the useful detail that replies are included in the result, but says nothing about read-only nature, permissions, pagination, ordering, or volume of comments returned.

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?

It is a single short clause with no filler, which is front-loaded, but the brevity comes at the cost of under-specification rather than true efficiency.

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 annotations and no output schema, the description is the only behavioral evidence an agent has, and it does not say what structure the comments come back in or how large a result to expect. For a read tool with a single required id, this leaves meaningful gaps.

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%, so the description must compensate. 'on a media id' does tell the agent that the single parameter is an Instagram media identifier, but it gives no format, source, or validity guidance for that id.

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?

It identifies the resource (comments plus their replies on a media item), which distinguishes it from ig_reply, but the phrase is a bare noun fragment with no verb. An agent must infer that this retrieves comments rather than posts or moderates them.

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?

There is no statement of when to use this versus siblings such as ig_media_list, ig_reply, or ig_check_media. The reader is left to guess the selection condition entirely.

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 entire burden: it doesn't say whether this is read-only, whether failed attempts are included, how far back history goes, whether results are ordered or paginated, or what permissions are needed. 'With status and permalink' is the only behavioral hint and is too thin 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?

The single fragment is front-loaded with zero padding, but its brevity comes from under-specification rather than discipline. Nothing wasteful, yet nothing earned beyond the bare noun phrase.

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, unannotated, output-schema-less history tool with eleven siblings, the description omits filtering behavior, ordering, retention window, and return shape. An agent could call it, but not confidently or correctly in edge cases.

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% for both parameters, and the description never mentions 'limit' or 'status'. It is ambiguous whether 'status' in the prose refers to a returned field or the filter parameter, leaving the agent to guess at valid values and paging semantics.

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 fragment 'Recent publish attempts with status and permalink' identifies the resource (publish attempt history) and hints at returned fields, but supplies no verb and no scope. It is not distinguishable from siblings like ig_media_list, ig_queue_list, or ig_insights 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?

There is no statement of when to call this versus ig_publish, ig_queue_list, or ig_insights, and no prerequisites or exclusions. The agent must infer that this is a post-hoc audit view rather than a live queue listing.

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 are provided, so the description carries the behavioral disclosure burden. It helpfully states the required instagram_business_manage_insights permission and implies a read-only insights operation, but it omits rate-limit behavior, return format, and error conditions.

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 short and front-loads the core resource and target options. The second sentence about permissions is useful, though the overall phrasing is fragmented and slightly informal.

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 two-parameter read tool with no output schema and no annotations, the description covers the target and gives metric examples plus a permission requirement. However, it leaves gaps around metrics syntax, default behavior, and when to choose this tool over siblings like ig_account.

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%: the target parameter is documented in the schema, while metrics is not. The description partially compensates by listing example metrics (views, reach, likes, shares, saves, watch time), but it does not specify formatting, defaults, or whether metrics is optional.

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 clearly states that the tool returns Instagram insights for either a media id or "account," and lists example metrics. It distinguishes insights from sibling tools like ig_media_list or ig_comments, though it does not explicitly contrast with ig_account, which could be confused with account-level insights.

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 offers no explicit guidance on when to use this tool versus alternatives such as ig_account, nor does it state exclusions. The only contextual note is the required permission scope, which is a prerequisite rather than usage 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?

No annotations are provided, so the description carries the full behavioral burden. It implies a read-only listing and mentions engagement counts, but it does not disclose pagination behavior, recency window, authentication requirements, rate limits, or whether results are limited to the authenticated account.

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 concise sentence with no wasted words, and the key information is front-loaded. It is under-specified rather than verbose, so conciseness itself is strong.

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 list tool, the description conveys what is returned at a high level (posts plus like/comment counts), but it omits essential context: no annotations, no output schema, and no documentation for the only parameter. An agent would have to guess about pagination, limits, and result scope.

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 tool has one optional parameter, limit, whose schema description coverage is 0%. The description does not mention the limit parameter at all, so its meaning, default, maximum, and effect on results are completely undocumented.

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 clear resource and content: recent posts on the account, including like and comment counts. It is distinguishable from a media-specific checker like ig_check_media, but it does not explicitly position itself against analytics or comment-focused siblings such as ig_insights or ig_comments.

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 provides no explicit guidance on when to use this tool versus alternatives, nor does it state when not to use it. Usage is only implied by the phrase 'recent posts.'

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 and discloses important traits: it blocks until Instagram finishes, reels may take 1-5 minutes, dryRun validates without posting, and duplicate media is refused unless force is set. It still omits permissions, error/response behavior, and irreversibility details.

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 compact sentences with the core action, blocking caveat, validation recommendation, and duplicate-protection behavior front-loaded. There is no wasted text.

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 complex 19-parameter publishing tool with no annotations and no output schema, so the description needs to cover more invocation context. It covers the critical blocking/dryRun/duplicate behavior but omits required parameter combinations such as type versus specFile, most parameter meanings, authentication expectations, and failure behavior.

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 only 37% for 19 parameters, so the description needs to compensate. It adds meaning only for dryRun, force, and duplicate-media handling, leaving most parameters such as type vs specFile, caption vs captionFile, trial, collaborators, and media shape unexplained.

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: 'Publish to Instagram NOW.' The emphasis on NOW and blocking behavior helps distinguish it from scheduled or queued publishing siblings, but it does not explicitly name an alternative tool.

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 clear guidance for dryRun and force, including validating first and overriding duplicate-media refusal. However, it does not explicitly say when to choose ig_publish over ig_schedule, ig_check_media, or queue-related siblings.

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 are provided, so the description carries the full behavioral burden. It implies a mutation but does not state whether cancellation is reversible, what permissions are required, what happens to an item that is not pending, or what the response looks like.

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 zero wasted words. It is appropriately sized for a simple one-parameter tool.

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, no output schema, and an undocumented required parameter, the description is too sparse. It should at least identify what the id refers to and what happens on success or 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?

Schema description coverage is 0% and the single parameter 'id' has no description in the schema. The tool description does not clarify whether this is the queue item ID, the media ID, or another identifier, leaving a meaningful gap.

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: cancel a pending queue item. It is immediately clear what operation is performed, though it does not explicitly differentiate this from sibling tools like ig_queue_retry or ig_queue_list.

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?

There is no guidance on when to use this tool versus alternatives, nor any preconditions beyond the word 'pending'. The agent must infer that this is for removal of queued items and not for retrying or listing them.

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. 'List' signals a read operation and the parenthetical discloses the key behavioral distinction between pending/running and full history, but it omits return format, ordering, pagination, and permission 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 words. The default scope is stated first and the parameter behavior is appended compactly.

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 one-parameter list tool with no annotations or output schema, the description covers the core scope and flag behavior. It still leaves gaps around return values, ordering, and how it differs from adjacent history-oriented tools.

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%, so the description must compensate for the single boolean parameter. It does so effectively by explaining that all:true returns full history while the default is pending/running, giving the boolean meaningful behavior beyond its bare type.

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 ('List') and resource ('queue items') and clarifies the default scope as pending/running. It does not, however, distinguish this from siblings like ig_history or explain why one would choose this list over that one.

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 implied by the default pending/running scope and the all:true full-history mode. There is no explicit guidance on when to use this versus ig_history or how it relates to queue action tools such as ig_queue_cancel and ig_queue_retry.

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 are provided, so the description carries the full behavioral burden. It identifies eligible item states but says nothing about mutation effects, whether the retry is immediate or deferred, permission requirements, idempotency, or what happens to the item's existing schedule.

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, which is good. However, its extreme brevity is under-specification rather than effective conciseness, and it provides no structure around the optional 'when' parameter.

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, no output schema, and two parameters at 0% schema coverage, this description is too thin. It does not explain the action's effect, the role of 'when,' or what the caller should expect after rescheduling.

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%, so the description must explain the parameters. It does not: 'id' is only implicitly referenced by 'queue item,' and the optional 'when' parameter is not mentioned at all, leaving its meaning and format completely undefined.

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 verb and resource: 'Re-schedule' a 'queue item.' It also narrows scope to failed/cancelled/pending items. It does not, however, distinguish this tool from siblings such as ig_queue_cancel or ig_schedule, 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?

The description implies usage by naming eligible item states ('failed/cancelled/pending'), but it never explicitly says when to choose this over ig_queue_cancel or ig_schedule. There are no prerequisites or exclusions, leaving alternatives 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?

With no annotations, the description carries the full burden; it does disclose the two most important traits — the reply is public and the text should be user-confirmed. It omits whether the reply can be edited or deleted, whether auth/ownership of the account is required, and any rate limits, leaving real behavioral gaps for a write 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?

Two short sentences, front-loaded with the action and immediately followed by the safety constraint. 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?

For a simple two-parameter, no-output tool the description covers the critical public-write warning, but it leaves both parameters undocumented and gives no hint of the response, which is a real gap at 0% schema coverage.

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%, so the description must compensate, and it says nothing about the two parameters. An agent must guess that commentId identifies the parent comment and that message accepts only plain text (no media, no mention syntax).

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?

"Reply to a comment" gives a specific verb plus resource, which separates it from ig_comments (reading) and ig_publish/ig_schedule (posting new content). It does not explicitly name any sibling as the alternative, so differentiation is inferred rather than stated.

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 implies usage (when someone has commented and you want to respond) and adds a workflow gate: confirm the text with the user first. It never says when NOT to use it (e.g., vs ig_publish for top-level posts, or ig_comments to just read), so guidance is only implied.

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 are provided, so the description carries the full burden. It usefully discloses that publication is handled by the systemd timer and references `ig scheduler install`, but it omits permissions, failure behavior, idempotency, and what happens to the queued item after scheduling.

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 tightly written sentences, front-loaded with the core action. The scheduling format examples and timer note are compact and earn their 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?

For an 18-parameter scheduling mutation with no annotations, no output schema, and low schema coverage, the description is too thin. It explains `when` and the timer mechanism but leaves most operational details uncovered.

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 only 39% across 18 parameters. The description adds valuable format examples for the required `when` parameter, which has no schema description, but it does not compensate for undocumented fields like type, media, caption, collaborators, or trial semantics.

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 clear verb and resource: 'Queue a post for later.' This distinguishes scheduling from immediate publishing at a high level, though it does not explicitly name ig_publish or other queue-related siblings.

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 implied by 'for later,' but the description does not explicitly say when to use this instead of ig_publish or how it relates to ig_queue_list, ig_queue_cancel, or ig_queue_retry. It also allows 'when': 'now', which blurs the boundary with immediate publishing.

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