emma-for-agents

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

Beyond the annotations, the description discloses concrete effects: the site becomes indexed, the notice is removed, free-plan limits apply, and there is no expiry, plus the keeper is notified on WhatsApp. It also documents the auth mechanism (site key as Bearer token) and the code's 30-minute, single-use validity — rich context that annotations alone do not convey.

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 purpose and outcome are front-loaded and every sentence carries useful information. It is somewhat dense and repeats the WhatsApp number and 'agent code' details already present in the schema, which is a minor structural inefficiency rather than wasted prose.

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 complex, open-world tool that depends on an out-of-band human interaction, the description covers the trigger flow, required inputs, auth, and resulting state changes. With an output schema present, return values need not be explained, and nothing essential for correct invocation appears to be 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 description coverage is 100%, so the schema already documents site_key, pairing_code, and guardian_whatsapp thoroughly. The description restates the code and keeper-number flow ('pass it with the keeper's number') and the Bearer-token requirement, but adds no new syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 opens with a specific verb and resource ('Confirm your preview with your keeper') and explains the outcome ('The site becomes confirmed: indexed, notice removed...'). It is clearly distinguishable from siblings like create_site and site_status, which handle creation and readback rather than committing a confirmation.

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 lays out the prerequisite flow in detail — the keeper writes 'agent code' to Emma, receives an 8-character code, and the caller must pass that code plus the keeper's number. However it never explicitly names an alternative or states when *not* to use this tool (e.g. relative to talk_to_emma), so it stops short of full routing 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 only give generic hints (readOnlyHint=false, openWorldHint=true, not idempotent); the description adds the real behavioral payload: preview is not indexed, carries a 'preview' notice, allows 10 edit messages, no image generation, expires in 30 days unless confirmed, returns URL plus a once-shown site key, and that creating accepts the CGV. This is far beyond what the annotations convey.

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 preview constraints, then the confirmation path and pricing/legal note. Dense but nearly every clause carries decision-relevant information; the pricing and CGV sentences are the only mildly peripheral additions.

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?

Despite 9 parameters, a nested endpoints object, and a mutation with real consequences (expiry, preview limits), the description covers scope, side effects, expiry, return values, and the confirmation route. With an output schema present it does not need to detail return structure further.

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 baseline is 3, but the description adds cross-parameter semantics the schema cannot: pairing_code must be combined with guardian_whatsapp to yield an immediately confirmed site, and what each alone produces. It does not add format detail beyond the schema for the other 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?

States a specific verb+resource ('Create a website for an AI agent from its facts') and immediately distinguishes the outcome from siblings by describing the preview-then-confirm lifecycle and pointing at confirm_site. An agent can tell this apart from confirm_site/site_status without opening 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?

Explicitly covers the two creation modes: default preview (with its limits and 30-day expiry) versus one-step confirmed creation by passing guardian_whatsapp + pairing_code, and names confirm_site as the follow-up path. When-to-use and the alternative are both spelled out.

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 useful context beyond that: the authentication requirement (site key as Bearer token) and the shape of the returned status data.

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, zero padding, and the payload (what the caller gets back) is front-loaded before the auth note. Nothing in the description is redundant 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?

With annotations covering safety, an output schema covering return values, and full schema coverage on the sole parameter, the description supplies everything else an agent needs (resource identity, returned fields, auth). Only the absence of any when-to-use routing against siblings keeps it from being fully 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?

Schema description coverage is 100% and the single site_key parameter is fully documented in the schema, including the maxLength/minLength constraint and the fact that the Authorization header takes precedence. The description's mention of the Bearer token overlaps with that schema text rather than adding new meaning, so baseline 3 applies.

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 concrete resource (the caller's site) and enumerates exactly what it returns: URL, plan, remaining messages and images for the period. It reads clearly as a status/read tool and is distinguishable in spirit from create_site or talk_to_emma, though it never explicitly contrasts itself with those 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 only implied: the agent can infer this is the tool for checking plan/quota status, and the description adds one prerequisite (site key as Bearer token). There is no statement of when to prefer this over siblings like confirm_site, nor any exclusion conditions.

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 this is destructive, non-read-only, non-idempotent, and open-world. The description adds useful auth context by stating it requires the site key as a Bearer token, but it does not disclose what destruction may occur, rate limits, or other behavioral traits 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?

The definition is two concise sentences, front-loading the core purpose and examples, then adding the auth requirement. Every sentence earns its place without 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?

With an output schema, rich annotations, and 100% schema coverage, the description need not explain return values or parameter details. It covers purpose, examples, and auth, but could be stronger by explicitly routing against sibling tools or warning about live/destructive edits.

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 the baseline is 3. The description adds concrete examples of what the 'message' parameter can contain (description, capabilities, links, generate an image) and reinforces the image URL use case, giving meaning beyond the schema's generic 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 states a specific verb and resource: 'Edit your site by talking to Emma in plain words.' The examples of editable content (description, capabilities, logo/hero image, links, generate an image) further clarify scope and distinguish this from sibling tools create_site, site_status, and confirm_site.

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 when the tool is used — to edit an existing site via plain-language conversation — but does not explicitly name alternatives or state when not to use it. No sibling tool is mentioned for routing, so usage guidance remains implied rather than explicit.

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