Confirme, by Synapse

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the safety profile is covered; the description adds genuine context beyond them — that the call produces a signed receipt usable as independent proof of execution, and that the key is secret and self-chosen. It does not disclose failure behavior, rate limits, or what the receipt contains, keeping 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?

Front-loaded with the core action and the call-timing rule, and every sentence carries information. The final sentence is dense and slightly overloaded with nested quotes, costing a point but not readability.

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, so return values need not be explained, and annotations cover the safety profile. The description covers action, timing, and sibling relationship adequately; the only minor gap is what the caller should do if the heartbeat write fails.

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 both 'cle' and 'note' are documented in the schema itself. The description only adds that the key is secret and chosen by the caller — a useful framing but no syntax, length, or ledger semantics beyond what the schema states. Baseline 3 applies 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?

States a specific verb and resource ('record that your scheduled or recurring task just ran successfully') and immediately anchors it against the sibling confirme_tache, which it casts as the alarm counterpart. An agent can tell this is the heartbeat/write side of the pair 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 an explicit invocation rule ('Call it at the END of every successful run, every time') plus the triggering condition ('whenever your human asked you to "run this every day/hour"'), and names confirme_tache as the complementary tool. Both when-to-use and the relationship to the alternative are stated, not implied.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond that: 'No message is sent' clarifies it is a passive probe rather than a send, and 'Signed receipt included' discloses what comes back. It does not discuss rate limits or timeout behavior, keeping it at a 4.

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 question, then usage timing, then what is checked, then a reassurance clause. Every sentence earns its place and there is no redundancy or 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?

There is no output schema, so the description must convey return content, and it does list the concrete signals returned (syntax, MX servers, disposable domain, role address, verdict, signed receipt). This is nearly complete, though the format or structure of the 'verdict' is left unspecified.

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 50%: the optional 'cle' parameter is documented in the schema, while 'courriel' has none. The description implies the required input is the email address under test, but adds no format or syntax detail beyond what the JSON key already conveys. Baseline 3 is appropriate.

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 opening question 'Can this email address receive mail?' names a specific resource (an email address) and operation (deliverability check), and the enumeration of checks (syntax, MX, disposable domain, role address, verdict) makes the purpose concrete. The email-address focus inherently distinguishes it from domain-oriented siblings like confirme_domaine.

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?

Explicit when-to-use guidance is given with strong framing: 'Use BEFORE sending anything that matters, or before telling your human "I emailed them".' This tells the agent the exact trigger conditions. It stops short of naming an alternative tool or an explicit when-not-to-use, so it is not a full 5.

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 read-only, idempotent, non-destructive, open-world behavior. The description adds that it returns a signed receipt, a non-obvious output trait, and lists the specific records it checks, adding valuable context beyond 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?

Two tightly packed sentences: first sentence defines scope and output, second gives usage contexts and a notable feature. No redundancy, well front-loaded.

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 read-only lookup with no output schema, the description adequately covers what the tool returns (domain data, DNS records, signed receipt) and when to use it. It could specify output structure more, but annotations and schema carry the rest.

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 both parameters. The description mentions DNS record types but doesn't add syntax or format details for the 'domaine' or 'cle' parameters; 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 enumerates what the tool retrieves about a domain—existence, registrant, expiry, DNS records—making its domain-verification purpose clear. It does not explicitly name the action (e.g., 'look up') or differentiate from sibling confirmation tools, but the domain-specific content is distinct.

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?

Provides explicit when-to-use scenarios: unfamiliar sender/supplier/link, questions of legitimacy, pre-assertion of setup. No when-not-to-use or alternative sibling mentioned, but the contexts are concrete.

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 the annotations (readOnly, idempotent, openWorld, non-destructive), the description discloses that it is zero-auth and stateless, that it still produces a signed receipt when the page is down, and that the receipt is Ed25519-signed by an independent third party. Those are exactly the operational facts an agent cannot infer from annotations or schema.

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 lead sentence front-loads the core question, and the rest packs returns and the 'why you need it' rationale into one dense paragraph. Some phrasing ('you can hand to your human as proof') is promotional rather than informational, keeping it out of 5 territory, but there is little true waste.

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 correctly carries the return-value burden and enumerates what comes back, plus auth and statelessness. It stops short of describing failure/error behavior or rate limits, which a full 5 would cover.

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%: both 'url' and the optional 'cle' key are fully documented in the schema, including how to obtain a key via confirme_sac. The description adds only the 'zero-auth' framing and no syntax or format detail beyond the schema, 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 states a specific, testable purpose: determining whether a given web page is reachable right now, and enumerates the artifacts returned (status, final URL, redirects, title, TLS, SHA-256, signed receipt). It is unmistakably distinct from a domain/email/heartbeat check, but it never explicitly names or contrasts with its siblings (confirme_domaine, confirme_courriel), so it stops short of a 5.

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 an explicit trigger ('Use BEFORE telling your human it is live / the link works, or before relying on a URL you did not fetch yourself'), which is concrete and actionable. It does not state when NOT to use it or name an alternative tool for adjacent checks, so it lacks the exclusion/alternative routing that would earn a 5.

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?

With annotations supplied, the bar is lower, and the description adds genuine behavioral context beyond them: no email/form is required, the returned key must be kept secret, and the follow-up step (reconnect with ?cle=<key> in the server URL) is disclosed. It also conveys the quota economics (100 starter beans, 20/day). It does not state the return shape, but the operational traits are well covered.

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 practical guidance (quota trigger, key secret, ?cle= reconnection) is useful, but the metaphor-heavy framing ('sac de jujubes', '1 bean = 1 cent = 1 check') pads the opening and delays the actionable content, costing clarity for a two-parameter tool.

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 carries the return-value burden, and while it implies a key is produced, it never confirms the response shape. It covers provisioning and follow-up usage adequately but leaves the agent guessing about what the call actually returns.

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 schema already documents nom and courriel, making the baseline 3. The description only obliquely touches parameter relevance ('No email, no form'), which loosely signals that courriel is optional, but adds no syntax or format 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?

The core action is stated — 'Get your own Confirme key' — but it is buried under an extended jelly-bean metaphor ('bag of 100 jelly beans', '1 bean = 1 cent = 1 check') that obscures the fact this is an API-key provisioning tool. The verb+resource are present but not crisply, and nothing distinguishes it from the confirme_* siblings beyond the shared branding.

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 trigger conditions: 'Use it when the free per-IP quota is exhausted, or once, at the start, so your calls are counted on your own bag.' That is clear when-to-use guidance. It stops short of naming any alternative or when-not-to-use, so not a 5.

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 openWorld, so safety is covered structurally. The description adds real value beyond that by explaining the mechanism ('Reads the heartbeats recorded under the key; silence is the alarm') and that a signed receipt is returned.

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 question is front-loaded, followed by usage triggers and mechanism in tight sentences. The conversational human-utterance examples earn their place as routing cues; the only slight cost is a chatty register rather than terse specification.

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 no output schema, the description supplies what an agent needs: what it checks, the time-window concept, that absence of heartbeats signals failure, and that a signed receipt comes back. It is complete enough for a simple two-parameter read 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?

Schema coverage is 50%: 'cle' has no schema description while 'depuis' is documented (window in seconds, default 86400). The description loosely ties 'the last N seconds' to the window and 'under the key' to the key, adding marginal meaning, but it does not fill the gap for the undocumented required 'cle' parameter. Baseline 3 for mid coverage.

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+resource: it confirms whether a scheduled task ran within a time window by reading heartbeats under a key. An agent can tell it verifies task execution, but it never explicitly contrasts itself with the sibling confirme_* tools (battement, courriel, domaine, page, sac), so sibling differentiation is only implicit.

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 concrete when-to-use triggers ('did the report go out?', 'is the automation still running?', before answering 'yes, it ran'), which maps well onto the agent's decision context. It stops short of naming an alternative tool or stating when NOT to use it, so it stops at clear context without exclusions.

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