noback

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

Adds substantial behavior beyond the annotations: apps are deleted after 30 days if unused and without app.net, claimUrl is private and only for that person, and appId/editKey must be retained for updates. It also clarifies that no account or token is required. This is exactly the lifecycle, privacy, and credential context an agent needs for a create operation.

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 constraint is front-loaded in the first sentence, and most of the content is useful operational guidance. It is a dense paragraph rather than a tightly structured list, and some conversational instructions could be separated, but it is not 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?

There is no output schema, but the description still names the important return/state fields: message with openUrl, claimUrl, appId, and editKey. It also covers deletion policy and next-step behavior. It falls short on input selection (html vs zipBase64) and does not mention validate_app, but it is largely complete for the tool’s complexity.

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 schema documents html and zipBase64, including that zipBase64 is an alternative to html, but name is undocumented. The description adds no input-level meaning and does not clarify that at least one of html or zipBase64 must effectively be supplied. With 67% schema coverage, the schema carries most of the burden, so this is adequate but has a clear 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?

States a specific verb and resource ('Publicá' an app) plus a key scope condition: no account or token. It also distinguishes this from update_app by saying not to create another app when publishing changes to the same 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?

Gives clear workflow guidance: publish, relay the message, ask once about saving, and use update_app for changes to this same app. However, it does not reference validate_app or get_sdk, so sibling alternatives are only partially covered.

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 destructiveHint=false, so the safety profile is covered and the description does not contradict it. It adds that the entire SDK.md is returned (not a summary or excerpt), which is useful, but says nothing about size, freshness, or whether the content is truncated.

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, no filler: the prerequisite instruction comes first and the return value second. Every clause carries information an agent needs before calling.

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 documentation fetch with no output schema, the description supplies the key missing piece: what the call returns (full SDK.md) and when to make it. It falls short only on undefined domain terminology ("contrato de noback") and on any hint about document size or versioning.

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 the baseline is 4; there is nothing for the description to disambiguate beyond confirming the call needs no arguments, which the empty schema already makes obvious.

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 concrete outcome: it returns the complete SDK.md, a documentation artifact. The verb is imperative ("Leé primero") rather than a description of the operation, and "contrato de noback" is unexplained jargon, but an agent can still tell this is a full-document fetch distinct from the create/update/validate 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?

"Leé primero... para escribir o cambiar una app" gives an explicit trigger: call this before writing or modifying an app, which maps onto create_app and update_app without naming them. No exclusion is stated for validate_app, so it is a clear context rather than a complete when/when-not rule.

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 it as a non-read-only but non-destructive write; the description reinforces this by promising that app.db collections/fields and localStorage keys are preserved so data and the shared link survive. It also adds a security constraint (never put editKey in the HTML or public link) and names the returned URLs. Rich, consistent context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action, followed by the data-preservation guarantee and the return/claim guidance. 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?

No output schema exists, yet the description covers the key return values (openUrl, claimUrl), the preservation semantics of an update, and the editKey handling rule. 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?

With 100% schema description coverage, the baseline is 3. The description restates that appId/editKey come from create_app and adds the editKey secrecy rule, but does not explain the html-vs-zipBase64 choice or its alternatives beyond what the schema already documents.

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 ('publicá una versión nueva de la misma app anónima') and pins down which app via appId/editKey from create_app, explicitly distinguishing it from the creation tool. An agent can tell this is a redeploy/update, not a create, 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?

Gives clear conditions: use it with the appId and editKey returned by create_app, and hand the person openUrl while treating claimUrl as private/optional. It does not contrast against validate_app or explain when not to re-publish, but the primary usage context is unambiguous.

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 establish a safe read operation (readOnlyHint=true, destructiveHint=false); the description adds non-obvious context: anonymous-mode limits and that anonymous apps have no app.net namespace. It does not mention rate limits or the shape of validation results, which keeps it below 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 short front-loaded sentences with no filler: what it does, how to remediate (fix/warnings), and a key constraint. The remediation sentence is slightly clipped but still 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?

Only two optional, fully-documented parameters, no output schema, and annotations covering the safety profile; the description supplies the missing workflow context (don't publish, fix errors, anonymous limits). Adequate without being exhaustive about returned validation payloads.

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 both html and zipBase64 are already documented with content requirements. The description names both inputs and hints at the anonymous limits but adds no format or constraint detail beyond the schema, matching the baseline 3.

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 (validate) and the two accepted input resources (html or zipBase64), plus the crucial scope qualifier 'sin publicar' (without publishing), which separates it from create_app/update_app. Sibling names are not used explicitly, so the differentiation is implicit 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?

Gives clear operative guidance: use fix to correct errors, review warnings, and notes the anonymous-mode limits as the operating context. It implies 'use this before publishing' but does not explicitly point to create_app/update_app as the follow-up path.

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