DiviMail

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds auth context not in the annotations ('No token needed, just the @divindi.io address') and steers subsequent behavior when the balance is low. It stops short of describing the shape of the returned balance (units, decimals), but that is a minor gap for a read-only lookup.

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 purpose, then the call-order guidance and the low-balance remedy. Every clause carries actionable information with 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 single-optional-parameter, read-only lookup with no output schema, the description covers purpose, prerequisites (no token), and next steps. The only missing piece is what the balance response actually looks like, which is a modest omission given the tool's simplicity.

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 parameter description already explains that the address can be omitted when signed in. The description reinforces the domain constraint ('just the @divindi.io address'), which is a small addition, but it adds no format or syntax detail beyond the schema. 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 ('Check how much USDC a DiviMail address has') and ties it to the concrete use case of sending email or paying. This clearly separates it from siblings like divimail_send, divimail_pay, and divimail_inbox without needing to open 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 when-to-use guidance ('Call before divimail_send or divimail_pay if unsure') and a concrete follow-up path ('if low, use divimail_request_topup'). It names both the trigger condition and the alternative action, leaving nothing 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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: auth is unnecessary under app sign-in, and the default page size is 20. It stops short of describing pagination or the shape of returned messages, which is the remaining 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?

Three tight sentences, front-loaded with purpose followed by the workflow and the exclusion. Every clause carries routing or behavioral 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 read-only list tool with full annotation coverage and zero required parameters, the definition covers purpose, workflow and auth adequately. Without an output schema, a brief mention of what fields a listed message exposes would close the last gap.

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 each parameter already carries a description explaining its role, including the conditional nature of email and token. The description's note that no token or address is needed when signed in largely restates the schema rather than adding new syntax or format guidance, 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 names a specific verb and resource ("lists received emails") and scopes it to the agent's @divindi.io address. It explicitly contrasts with divimail_sent for outbound mail, so an agent can separate the two without opening either 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 an explicit sequence: call this first, then divimail_read with a messageId, then divimail_mark_read. It also names the alternative (divimail_sent) and the condition that selects it, leaving no routing ambiguity among siblings.

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 idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context the annotations do not carry: the auth model ('When connected through an app sign-in, no token or address is needed') and the state-management intent of avoiding duplicate handling.

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 action and its rationale, then the prerequisite call, then the auth shortcut. Every clause carries information an agent needs before invoking the 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?

For a three-parameter, one-required mutation with no output schema, the description covers purpose, ordering, identifier consistency and auth. The only gap is error/edge behavior (what happens if the message is already read or the ID is unknown), which is partly mitigated by idempotentHint=true.

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 email, token and messageId are all documented in the schema, including the 'omit when signed in' behavior. The description only adds the constraint that messageId must match the one used in the preceding read/inbox call, which is a small increment over the schema's 'Message ID from divimail_inbox'.

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 ('Mark an email in your agent's inbox as read') plus the reason ('so it is not handled twice'). The sibling set contains no other mark-state tool, so the purpose is unambiguous, though it never explicitly says what it is not (e.g., it does not mark unread or delete).

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 sequencing: 'Use after divimail_read (or divimail_inbox) with the same messageId', naming the two sibling tools that produce the required identifier. It lacks a when-not-to-use clause (e.g., already-read messages or messages not in the inbox), which keeps it short of 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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds real value by saying the full body and details are returned and that app sign-in removes the credential burden, though it says nothing about how a missing or foreign messageId behaves or about pagination/size limits on large messages.

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, front-loaded with what the tool returns, followed by sequencing and auth notes. No filler or 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?

For a read-only single-record fetch with full annotation coverage, the description is nearly sufficient. The gap is the return shape: 'body and details' hints at content but does not indicate whether attachments, headers, or HTML vs plain text are included, which matters since there is no output 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 description coverage is 100%, so the schema already explains email, token and messageId in comparable detail; the description's 'messageId from that list' largely restates the schema. Baseline 3 is appropriate since the description adds no new syntax, format or validation detail for the 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 and resource ('Open and read one email in full (body and details)') plus the source mailbox, which clearly separates it from divimail_inbox (listing) and divimail_mark_read (state change). An agent can select it 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 an explicit workflow: call after divimail_inbox, pass a messageId from that list, then optionally call divimail_mark_read. It also names the auth condition under which token/address are unnecessary, so the prerequisites are spelled out rather than 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?

The annotations already declare the key traits: this is a write that is not read-only, not idempotent, and open-world. The description still adds real behavioral context beyond that: the apiKey is returned only once and must be saved, and with publicKey only the public key is stored. It does not cover failure modes such as an alias already being taken or what happens on a second call.

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 description is front-loaded with the action and the one-time constraint, then moves through the auth alternatives and the parameter selection rule in a tight sequence. It is dense but every sentence carries information; only the parenthetical enumeration of sign-in options feels slightly packed.

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 explain what is returned; it does so by noting that the one-time apiKey is returned for provision and publicKey modes, and that nearAccountId returns none. Together with the annotations and the fully documented schema, an agent has enough information to call this tool correctly, with only error handling left unaddressed.

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 a baseline of 3 would be acceptable. However, the description adds meaning the schema does not fully convey, including the mutual exclusivity of the three credential modes, the relative ease of provision:true, and the consequence that nearAccountId requires no apiKey. That goes beyond restating 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: creating an @divindi.io email address for an AI agent, with the one-time registration scope made explicit. It is clearly distinguishable from siblings such as divimail_send, divimail_inbox and divimail_login, which are reference tools / follow-on steps rather than registration.

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 explicitly says 'Call this once to create the address' and names the sequence that must be followed: app connection sign-in, or divimail_login, or divimail_challenge + divimail_authenticate. It then gives mutually exclusive selection guidance for the credential mode ('Use exactly one of...') and marks provision:true as the easiest path.

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 a non-read-only, open-world, non-idempotent, non-destructive operation. The description adds genuinely new behavioral context beyond them: a concrete cost of $0.01 USDC per email, and that credentials may be unnecessary in app sign-in mode. It does not describe the response or error behavior, which keeps it from 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?

Four short sentences, front-loaded with the action and followed by auth, cost and escalation paths in descending order of importance. Nothing is padded, and the capability sentence at the end is a compact summary rather than 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 an 8-parameter mutation tool with no output schema, the description covers auth mode, cost, required-vs-optional content, and where to go on insufficient balance. It leaves the return value (message id, status) and any send failure modes unstated, which is the main remaining gap.

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 every one of the 8 parameters is already documented, including the from/token omission rules. The description's mention of plain text, optional HTML, CC and BCC largely restates 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?

States a specific verb and resource ('Send an email from your agent's @divindi.io address to any email address') plus the scope that any recipient domain is allowed. This clearly separates it from read-oriented siblings such as divimail_inbox, divimail_read and divimail_sent without the agent needing to open a 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 real routing guidance: no token or address needed under app sign-in, and points to divimail_balance and divimail_request_topup when the balance is low. It stops short of stating exclusions or failure conditions (e.g. what happens if funds run out mid-send), so it is strong but not a full when/when-not map.

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 open-world, so the safety profile is covered. The description adds genuinely new context beyond that: it states that app sign-in removes the need for a token or address, which is an auth prerequisite the annotations do not convey. It omits return shape and whether results are paginated or capped by the limit, which keeps 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?

Four short sentences, front-loaded with purpose before use cases and the sibling pointer. There is minor redundancy between 'See what emails your agent has sent' and 'lists sent messages for its @divindi.io address', but the second clause adds the address scope, so the cost is small.

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?

This is a simple read-only list tool with zero required parameters, full schema coverage and no output schema, so the description carries most of what an agent needs: purpose, use cases, the alternative sibling and the auth shortcut. It does not describe the returned message fields or ordering, a minor gap for a listing tool without an output 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 each parameter is already documented in the schema, including the default of 20 for limit and the sign-in behavior for email and token. The description only echoes the default limit and the auth shortcut, adding little syntax or format detail beyond structured fields. 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?

States a specific verb and resource ('lists sent messages') and scopes it to the agent's own @divindi.io address. It also explicitly contrasts with divimail_inbox, so an agent can tell the two apart without opening either 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 two concrete use cases ('confirm a divimail_send went out' or 'review history') and names the alternative sibling for the opposite case ('For received mail use divimail_inbox'). The routing decision is fully specified.

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