LivePublicator

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

Goes beyond the annotations by disclosing image constraints (landscape, >=1200 px wide) and the one-time upload-link fallback, neither of which is expressed in the schema or annotations. It is silent on whether an existing cover image is replaced and on any permission requirements for a draft, which slightly limits the behavioral picture.

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 sentences, each carrying distinct information (action, input modes, validation constraints, optionality/fallback), with the core action front-loaded and no repetition of schema content.

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 covers the non-obvious return path (one-time upload link) plus the constraints and fallback behavior, which is enough to call the tool correctly. It remains silent on lifecycle details such as whether re-adding replaces an existing image or whether this only works while the release is in draft.

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%, so baseline is 3, but the description adds real meaning: it frames image_url and image_file as alternative modes and explains the behavior when both are omitted (upload link), which the schema alone does not convey.

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 ('Adds a cover image') and scopes it to 'a draft press release', which cleanly separates it from siblings like create_release, publish_release, and update_release. An agent can identify the operation 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?

Explains the three input modes (URL, attached file, or neither to get a one-time upload link) and explicitly notes the step is optional because a default logo/headline cover is used otherwise. It does not reference sibling tools or the surrounding publish workflow, so it stops short of full alternatives 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?

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so mutation semantics are covered. The description adds genuine context beyond them: no credit is consumed, the text is not rewritten, all validation problems are returned in one pass, and the response includes a private preview link. It does not warn that repeated calls create separate drafts (non-idempotent), which is the main remaining behavioral gap.

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 core action is front-loaded in the first clause and the sentence count is low relative to the amount of information conveyed. The middle section ('length, structure, links, image size and content... Send the finished release') is slightly clipped and requires a second read, but there is little 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 17-parameter creation tool with no output schema, the description covers purpose, the validation return path, the preview-link output, credit behavior, and agency/company parameter conditions. Missing pieces are the draft's lifecycle after creation (how it is later edited or published) and duplicate-draft 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 coverage is 100%, so the baseline is 3, but the description adds account-type semantics the schema does not encode: company_name/company_website become optional for company accounts, and client_authorized only applies to agencies. That is meaningful conditional meaning layered on top of the per-field descriptions.

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 — saves a press release/announcement as a draft and validates it — and explicitly carves out that it neither writes the copy nor publishes the release, which separates it from publish_release. It stops short of naming or contrasting with preview_press_release, update_release, or fix_live_release, so sibling differentiation is only partial.

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 supplies concrete conditional guidance: company accounts may omit company name and website, while agencies must name the client company and set client_authorized to true. 'It does not publish' implicitly routes the agent to publish_release for going live. There is no explicit when-not clause or named alternative for revising an existing draft.

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 only say this is a destructive, idempotent, open-world write. The description adds substantial behavior beyond that: the URL is preserved, the previous version is retained as history, and the edit re-enters review before it becomes visible. The 24-hour window is a hard operational constraint the annotations do not express.

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 short sentences, front-loaded with the action and the time constraint, then consequences, then the hard limit. Every sentence carries distinct information with no repetition of the title or schema.

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 output schema, the description must explain the effect of the call, and it does: same link, version retained, re-review before display. For a 12-parameter mutation tool with full schema coverage and rich annotations, nothing an agent needs to invoke it correctly 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 100%, so the baseline is 3, but 'Send only the fields to change' adds genuine partial-update semantics that the schema alone does not convey (it cannot distinguish merge from replace). No field-level detail is added, which is fine given the schema documents all 12 parameters.

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 ('Fixes the text of a published press release') plus a hard scope qualifier ('within 24 hours of it going live'). That scope implicitly separates it from the draft-oriented siblings update_release and publish_release, but it never names them, so an agent must infer the boundary.

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 states a clear use window ('within 24 hours of it going live') and an explicit exclusion ('After 24 hours the text can't be changed'), which is real when-to-use guidance. It stops short of naming the alternative tool to use for drafts or post-24-hour edits, leaving the routing 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description goes beyond that by naming the actual data categories returned, which helps an agent decide whether this call supplies the context it needs. It stops short of noting auth requirements or freshness of the credit count.

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 front-loaded sentence that carries real information with no filler. The enumerated list is long but each item maps to a distinct piece of account state an agent might need.

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 output schema, the description carries the burden of conveying the return shape, and it does so at a summary level by naming the four categories of account data. Slightly more detail on response structure or the credit-count semantics would complete 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?

The tool takes zero parameters and the schema is trivially complete, so there is nothing for the description to clarify. Baseline of 4 applies since no parameter ambiguity exists.

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 (shows) and resource (the signed-in account) and then enumerates exactly what the account view contains — company/agency identity, remaining publishing credits, auto-check vs. human-approval publishing mode, and agency client companies. This is unambiguous and easily separable from the release-oriented 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 the content: an agent would call it to discover account tier, credits, or publishing mode before publishing. However, there is no explicit when-to-use statement, no mention of prerequisites (e.g., that the caller must be authenticated), and no exclusions or alternatives 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?

The readOnlyHint/openWorldHint annotations already declare this as a safe, non-external read, so the bar is lower. The description earns credit by disclosing the possible return states and the conditional live-link field (no output schema exists to carry that), though it says nothing about behavior for an unknown or unauthorized release_id.

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 sentences, front-loaded with the resource and the state enumeration, followed by one sentence of usage context. No filler, nothing repeated from the title or annotations.

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 output schema, the description usefully enumerates the status values and the published link, which is the core of what an agent needs to interpret the response. It omits error/not-found behavior and scoping (account/workspace), which keeps it shy of 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?

There is a single required parameter with 100% schema description coverage, so the schema carries the definition. The description adds nothing about release_id format, source, or whether it must belong to the caller's account. Baseline 3 is correct when the schema does the heavy lifting.

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 resource (a press release) and enumerates exactly what it returns: draft, pending review, scheduled, live, plus the live link once published. That distinguishes it in practice from list_releases (plural, all releases) and publish_release (a mutation), though it never names a 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?

"Useful to check back on a release that was waiting for review" implies a polling/status-check use case, but there is no explicit when-to-use vs. when-not, and no alternative named (e.g., use list_releases to see all statuses at once). Usage is implied rather than stated.

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=true and openWorldHint=false, so the safety profile is covered. The description adds that results include status and links, which is useful return-shape context, but says nothing about ordering guarantees beyond 'latest' or how limit interacts with totals. Adequate against the lower annotation bar.

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 verb and resource, and every phrase (status, links) earns its place. Nothing redundant or 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?

A simple, zero-required-param read tool whose annotations cover the safety profile and whose one parameter is fully documented. Mentioning that responses include status and links compensates for the absence of an output schema. Only minor gaps remain, such as whether pagination or totals are exposed.

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 single limit parameter is fully documented, including default and ordering, so the schema does the heavy lifting. The description adds no further parameter meaning, which is the expected baseline here.

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 (Lists) and resource (the account's press releases and announcements) and adds what each item carries (status and links). It does not explicitly contrast itself with close siblings like get_release_status or preview_press_release, 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?

The listing framing implies when to reach for it (browsing recent releases), but there is no explicit when-to-use guidance, no prerequisites, and no mention of the alternative tools an agent might pick instead. Usage is inferable only from the tool's shape.

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 annotations: it returns all validation problems at once, produces a private page that expires after 7 days, requires no sign-in, and explicitly does not publish. That said, readOnlyHint=false is unexplained (a preview page is created), and nothing is said about regeneration or limits.

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 what the tool does and what to send, then closes with the key behavioral facts (all errors at once, 7-day expiry, publishes nothing). The field enumeration is dense but each item maps to a required input, so little is 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?

Covers the essential behavior for a 15-parameter, no-output-schema tool: no auth needed, batch validation feedback, preview expiry, and the no-publish guarantee. Missing only secondary details like regeneration behavior or size limits beyond those in the schema.

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%, so the baseline is 3, but the description goes further by enumerating the expected content set (headline, summary, body, key facts, quote with name and role, contact, company name/website, optional image) and flagging the image URL as conditional.

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 (preview a press release on LivePublicator) and explicitly separates itself from write siblings with 'This tool publishes nothing,' which distinguishes it from create_release and publish_release without needing their schemas.

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?

Tells the agent to 'send the finished release' and notes the preview page has a publish button, which implies this is the pre-publish validation step. It stops short of naming an alternative or stating an explicit when-not condition.

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 only provide coarse hints (not read-only, destructive, open-world, idempotent); the description adds the credit cost, the refund condition, the fast-path latency ('live link within seconds'), and the fallback path where a human review can hold the release up to 24 hours with a stated reason. That is substantial behavioral context an agent cannot infer from the structured fields.

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 purpose, then the gating condition, then cost/refund, then outcomes — no sentence is padding. It is slightly denser than necessary with credit and timing details packed into one run-on sentence, but nothing is 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?

There is no output schema, so the description must cover return values, and it does: a live link within seconds, or a pending-review message with reason and expected duration. Combined with the cost and refund rules, an agent has everything needed to call it and set expectations.

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 only two parameters exist, so the schema already documents both fields; the description reinforces the meaning of confirm ('the user saw the preview and said to publish') but adds nothing about release_id. Baseline 3 is appropriate when the schema carries the 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 resource ('Publishes a draft press release') plus the external side effect ('tells search engines about it'). This clearly separates it from create_release, update_release, and preview_press_release, and the draft-vs-live distinction is explicit.

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 a hard precondition — 'Only call this after the user has seen the preview and clearly said to publish, and set confirm to true' — which functions as both when-to-use and when-not-to-use. It implicitly routes the agent through the preview step before publishing rather than any sibling mutation tool.

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 cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), yet the description adds real value beyond them: partial-update semantics, that the whole release is re-validated, what is returned (problems or preview link), and that it costs no credit. It still doesn't say what happens to validation failures or whether the draft stays unpublished.

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 short sentences, each earning its place: mutation scope, return behavior, and cost. The partial-update rule is front-loaded and there is 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 12-parameter mutation tool with a fully documented schema, no output schema, and annotations covering the safety profile, the description covers the essentials: partial update, re-validation, return values, and zero credit cost. It is slightly thin on failure behavior but complete enough to invoke correctly.

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%, so all 12 parameters are already documented in the schema with constraints (word counts, character limits, item caps). The description adds only the generic partial-update rule, which is a baseline-level contribution, not parameter-specific detail.

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 (changes fields), resource (draft press release), and a meaningful scope constraint ('draft'), which implicitly separates it from siblings like fix_live_release and publish_release. It does not name any sibling explicitly, 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 'draft press release' and 'only the fields you send' phrasing implies when to use it (partial edits on drafts, not creation or publishing), but there is no explicit when-to-use/when-not guidance and no named alternative for cases like a missing release or a live one.

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