Proxylang website translation

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

Annotations already declare idempotent=true, destructive=false and openWorld=true, but the description adds context those hints can't carry: the old site stops on "move", sites share one limit, and the token/script tag/claim_url/free words are preserved. It doesn't state the response shape, but for this tool that omission is minor.

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 dense sentences plus a one-clause boundary rule; the primary use case is front-loaded and every sentence carries operational information. Nothing is padding.

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 3-parameter mutation tool with no output schema, the description covers motive, both action semantics, shared-limit behavior, and the localhost alternative. It could mention the cap interaction or what comes back after the change, but an agent has enough to invoke it 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% and the enum values for action already document "move" vs "add" (including the up-to-3 cap). The description reinforces when each action applies but adds no format or syntax detail the schema lacks, so the baseline 3 is correct.

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 resource (the trial's site) and the two distinct operations ("move" replaces it, "add" extends it), each with its effect spelled out. An agent can distinguish this from proxylang_start or proxylang_status 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?

It gives explicit triggering conditions for both actions (wrong website -> move; test/staging site -> add) and an explicit exclusion with a named alternative ("Not needed for localhost: use localhost_script_tag"). When, when-not, and the alternative are all 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=true, so safety and network scope are covered. The description adds that it inspects the live site and that a zero word count requires a browser visit to preview_url, but it does not describe the return shape or how the check is performed.

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 with no filler, and the primary check is front-loaded. The first sentence is phrased as a question rather than a direct statement, which is slightly less directive but still efficient.

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 should convey return values; it mentions words_translated and implies a tag-presence result, but does not describe the full response or preview_url sourcing. The prerequisite about a browser visit is helpful but leaves gaps for acting on the result.

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 agent_token parameter is fully documented in the schema. The description adds no further meaning about the token or its format beyond what the schema already provides, 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 states specific checks: whether the Proxylang tag is on the live site and whether words have been translated. It does not differentiate this from the sibling proxylang_status, which likely overlaps, and the question phrasing is slightly indirect rather than a clear verb+resource statement.

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 conditional prerequisite: if words_translated is 0, a real browser visit to preview_url is needed first. However, it never states when to call this tool versus proxylang_status or proxylang_next, so usage must be inferred.

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 declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful behavioral context beyond that: the payload must be shown verbatim, in the user's language, with <claim_url> substituted by the saved claim_url. That is presentation guidance the annotations cannot convey. It could go further on failure/edge behavior.

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 dense sentence that front-loads the return value, with the usage instruction parenthetically appended. Every clause carries information, though the parenthetical instruction could be split for easier scanning.

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 correctly carries the burden of explaining the return value and how to present it, including the <claim_url> substitution. For a one-parameter read-only tool this is close to complete, missing only error or retry 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 100% and the single agent_token parameter is fully documented in the schema as coming from proxylang_start. The description adds no extra meaning about the parameter, so the baseline of 3 is appropriate when the schema does the work.

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 resource: it returns message_for_user, the final setup message, and enumerates its contents (site works, claim link, fitting Proxylang features). It is clearer than the tool name 'proxylang_next' alone, though it does not explicitly distinguish this from proxylang_status or proxylang_check beyond the 'end setup' framing.

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 phrase 'the message to end setup with' implies this is called at the end of onboarding, giving implicit timing. However, it never explicitly says when to call it versus proxylang_status or proxylang_check, and lists no prerequisites beyond token reuse.

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 readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds genuinely useful behavior: the exact artifacts returned, that agent_token is consumed by the other tools, and critically that claim_url is 'sent once; save it' — which is the practical consequence of idempotentHint=false and something an agent must act on.

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 sentences, all load-bearing: the first covers action plus outputs, the second the required language decision, the third the trial/upsell framing. No filler and the most actionable content (claim_url warning) is front-loaded near the start.

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 fully carries the return-value burden: names each returned artifact and flags the one-time claim_url. Combined with the annotation set it covers safety, side effects, and continuation into the sibling tools, leaving no material gap for a 3-param starter call.

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 goes beyond it by supplying a selection heuristic for the languages array ('customers most likely speak and say why') and confirming that source_lang is auto-derived when omitted, which shapes how the agent should populate the params.

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 ('Set up Proxylang on a website') with the distinctive modifier 'with no signup', and immediately enumerates what the call produces (script tag, install steps, agent_token, claim_url). An agent can tell this apart from proxylang_status/check/next without opening any 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 explicit decision guidance for the language choice ('If the user named a language, use it; otherwise pick the one their customers most likely speak and say why') and explains the trial continuation path ('list other recommended languages after it'). It stops short of naming when to prefer a sibling tool, so it is clear context without explicit alternatives.

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=true, so the safety profile is covered. With no output schema, the description's enumeration of return contents (free words, expiry, claimed/paid) is genuinely useful, but it says nothing about authentication requirements, freshness, or whether the trial state can change between calls.

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 zero padding, and the most decision-relevant information (free words left) is front-loaded. It is a verbless fragment rather than a sentence, which slightly weakens framing but costs nothing in length.

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 one-parameter read tool with full schema coverage and annotations covering safety, the description supplies the missing piece — what the call returns — since no output schema exists. It stops short of explaining token provenance or when the reported trial state is meaningful.

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 agent_token parameter is documented in the schema as coming from proxylang_start. The description adds no parameter meaning beyond that, so the 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 the specific data the tool reports — free words remaining, trial expiry, and claimed/paid status — so an agent knows it is a trial/quota status reader. However, it uses no verb and does not differentiate itself from siblings like proxylang_check or proxylang_next, which an agent might plausibly confuse it with.

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 when-to-use statement, no precondition, and no mention of alternatives among the sibling tools. Usage (call it to learn remaining quota) is only inferable from the list of returned fields, and the description gives no guidance about when this is preferable to proxylang_check.

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 cover the safety profile (idempotent, non-destructive, open-world), so the bar is lower. The description still adds real value: it discloses partial-update semantics ('send only the fields to change') and a required read-reconnaissance step before writing, which the annotations 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?

Three sentences, front-loaded with the goal, then the workflow, then format rules and a doc pointer. Every sentence carries information; the external URL is a minor efficiency trade-off but earns its place by offloading the full field list.

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 output schema, the description plus annotations cover safety, prerequisites, update semantics, and color format. The only gap is return/confirmation behavior and the meaning of enum-like values (borderRadius, size), which the schema partially covers.

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 nested style object documents every field, so the baseline is 3. The description goes beyond that by specifying accepted color syntaxes (#hex, rgb(), hsl(), CSS names) and noting each color has a Light and Dark variant, which the schema does not state.

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 — restyle the language menu to match the site's look — which an agent can distinguish from the broader proxylang_change_site. It stops short of explicitly contrasting with any named sibling, so it lands at clear-but-undifferentiated.

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 an explicit prerequisite workflow: read the site's brand color, background, text color, roundness and dark mode first, then send only the fields to change. That is actionable context, though it never names alternatives or states when not to use this tool.

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