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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds genuinely new behavioral facts: it drives a real Chrome browser, opens platform upload pages, and closes the tabs afterward. It says nothing about failure modes if Chrome is unavailable or no user is logged in, 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?

Roughly three short lines, front-loaded with the action and scope, followed by the parameter note and return shape. Nothing is repeated or wasted.

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 annotations covering the safety profile and a real output schema defining the return shape, the description gives everything needed to invoke it correctly. Only the environmental precondition (Chrome must be available/authenticated) 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 coverage is 0% and the schema only offers an untyped string array with a null default. The description compensates well by naming the accepted values ("youtube", "facebook", "tiktok") and mapping the null default to "all". It does not address invalid or mixed-case platform strings.

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: opens each platform's upload page in Chrome and reports the logged-in account, plus the cleanup detail (tabs are closed after). It is clearly distinguishable from the write-oriented siblings (publish, publish_batch), though it never names them 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 pre-publish/preflight use case is implied by the 'which account is logged in' framing, but there is no explicit statement of when to use this versus status or history, nor any prerequisite such as a running Chrome session.

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 closed-world, so the safety profile is covered. The description adds genuinely new behavioral detail: results are ordered oldest-to-newest, and data is read from a local file at <state dir>/history.jsonl. It does not say whether history is truncated or session-scoped, so it sits at an adequate 3.

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 sentence, front-loaded with the result set and its ordering, with the storage location trailing as supporting detail. Nothing redundant.

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 an output schema present and annotations covering safety, the description only needs to convey scope and the parameter's effect, which it does. The remaining gap is whether history is bounded (e.g., only this session or the whole state file), which an agent could reasonably want.

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 the single `limit` parameter has no description in the schema beyond a default of 20. The description compensates by defining what `limit` controls (how many of the most recent results are returned) and by clarifying the resulting ordering ('newest last'), which is meaning the schema does not carry.

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 resource (posting results) and the exact selection rule ('the last `limit` results, newest last'), so an agent knows it is a retrieval of past posting attempts. It never mentions `status` or `check_accounts`, so sibling differentiation is only implicit, which keeps it out of the 5 tier.

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 `status` (current state) or `check_accounts`, and no exclusions or prerequisites. The use case (reviewing recent posting outcomes) must be inferred from the phrase 'posting results'.

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?

Adds real context beyond the annotations: it runs through the user's logged-in Chrome (auth model), options vary per platform, dry_run stops before the final click, and keep_tab keeps the tab open for inspection. It does not warn that publish is non-idempotent (a retry may create a duplicate post) or describe failure handling, which is the notable gap given the annotations declare openWorldHint and idempotentHint=false.

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 action and the approval precondition, then a compact per-parameter glossary with no filler. It is dense but every line conveys operative detail; only minor cost is the terse line-wrapped enumeration style.

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?

An output schema exists, so skipping return-value detail would be fine, yet it still sketches the result shape. For a high-stakes, open-world, one-shot publish action, the remaining gap is error/retry behavior and what happens if the Chrome session is not logged in.

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 carries the full burden and does: each parameter is explained with platform-specific meaning (caption = YouTube description / FB reel description / TikTok caption), title constraints (required for YouTube, max 100 chars, ignored elsewhere), schedule_at format with a worked ISO 8601 example, per-platform option keys, and dry_run/keep_tab 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?

States a specific verb and scope: upload one video to one platform via the user's logged-in Chrome, then publish or schedule. The 'one video to one platform' phrasing implicitly separates it from publish_batch, and the platform/video/caption mapping makes the resource concrete.

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 gates invocation on prior user approval of this exact post (video, text, platform, time), and gives a concrete sequencing rule: use dry_run first for a new template, and omit schedule_at to publish now. This is what/when guidance an agent can act on.

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 annotations, it discloses important behavior: all jobs are validated first and nothing runs if any job is invalid, jobs run in parallel tabs subject to max_parallel, only one job per platform runs at a time, and results are returned in input order. These details materially help an agent anticipate side effects and execution semantics.

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 compact and front-loaded: it states the operation, approval guard, job shape, validation/execution behavior, and return shape without filler. Every sentence carries useful 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 the output schema and annotations, the description covers most of what an agent needs: batch purpose, job fields, atomic validation, parallelism, and return ordering. It still omits dry_run/keep_tab semantics and does not clarify what happens if a job fails after validation.

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 0% schema description coverage, the description partly compensates by documenting the jobs item structure and explaining max_parallel. It leaves dry_run and keep_tab undocumented, so parameter semantics are only partially covered.

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 ('Run several posts') and gives concrete batch examples, clearly distinguishing it from the single-post sibling publish. An agent can immediately tell this is the batch-publishing 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 a strong usage prerequisite ('Only call this after the user approved every post in the batch') and batch scenarios such as one video to three platforms or a week of scheduled posts. However, it does not explicitly name publish as the alternative for single posts or state when not to batch.

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, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered by structured data. The description adds that the call surfaces live operational state (running jobs, open tabs, last results), which hints it is a snapshot read with no side effects, but it does not say whether the call blocks, whether it fails when disconnected, or how stale the data is.

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 sentence, front-loaded with the single most important question an agent would ask, followed by a compact field list. No filler and nothing to trim.

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 an output schema present and zero parameters, the description does not need to explain return values, and the rich annotations cover safety. What remains missing is only the usage context (when to reach for this instead of check_accounts or history), which is a minor gap for such a simple diagnostic tool.

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. Baseline 4 applies for a no-arg tool.

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 frames the tool as a connectivity/diagnostic check ('Is the Chrome extension connected?') and enumerates the payload (versions, running jobs, open tabs, last results), which is specific enough to distinguish it from publish/publish_batch. It lacks an explicit verb like 'returns status of', but the question form plus the field list makes the purpose unmistakable.

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 siblings. A natural use case — verifying the extension/server is alive before publishing, or diagnosing a failed publish — is only inferable, and the relationship to check_accounts (also a 'check' tool) is left entirely unaddressed.

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