FirstKey

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

With no annotations, the description carries the full behavioral burden. The word 'Read' clearly signals a non-mutating operation, and 'cycles ledger' provides useful scoping. It does not describe error cases or output format, but for a simple balance read these are minor omissions.

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 a single sentence with no filler. It front-loads the action and resource without wasted words.

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 operation with full schema coverage, the description plus input schema is sufficient for an agent to select and invoke the tool correctly. The term 'cycles balance' makes the expected return value obvious even 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 description coverage is 100%, and the schema already defines 'principal' as an 'ICP principal (text form)'. The description adds no new parameter semantics beyond reinforcing that the principal is whose balance is being read, 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 states a specific verb ('Read') and a specific resource ('an ICP principal's cycles balance on the cycles ledger'). This clearly differentiates it from sibling tools, which are all write/deploy/claim operations.

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 use case is implied: call this when you need to check a principal's cycles balance. However, there is no explicit guidance about when not to use it or which alternative to prefer, so the guidance remains implicit rather than explicit.

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 no annotations, the description must carry the behavioral burden. It discloses the effect (grant lands on cycles ledger and funds the first deploy) and the one-time limitation. However, it does not specify what happens on a second call (error, no-op, etc.) or the return format, leaving a gap for a mutating tool.

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 three concise sentences, front-loaded with the action and the critical constraint. There is no fluff or repetition; every sentence 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?

For a simple one-parameter tool with no output schema, the description covers the purpose, effect, and key constraint. It omits error behavior on repeated claims, but this is a minor gap given the tool's simplicity. The description is sufficiently complete for an agent to know what to expect.

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 schema already describes the agent parameter accurately. The description adds no additional meaning beyond what the schema provides, so it does not enhance parameter understanding. 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 description clearly states the verb 'claim', the resource 'one-time free 1T cycles grant from the FirstKey faucet', and the recipient 'an agent principal'. It also names the one-time constraint, which distinguishes it from sibling tools like check_cycles and get_fuel_link that serve different purposes.

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 states the 'one claim per principal, ever' constraint, which is a clear when-not to call repeatedly. It implies usage for the first canister deploy, but does not explicitly mention alternative tools or when to use them. This is adequate but not exhaustive.

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 no annotations, the description carries the full burden. It discloses that the private key is returned exactly once and never stored, which is critical behavioral information. It also clarifies that no registration is involved. It does not mention any side effects or prerequisites, but for a wallet generation tool this is adequate.

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 two sentences, front-loaded with the primary purpose and outputs, and includes the key behavioral caveat (one-time return, no storage) without any fluff. Every sentence 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?

The tool is simple (no params, no output schema), but the description explains what is returned (principal and PEM key) and the one-time nature. It does not specify the exact return structure (e.g., JSON field names), but given the low complexity and the explicit mention of the two outputs, it is sufficiently complete for an agent to call 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?

The tool has zero parameters, and the schema coverage is 100% (empty schema). Per the rubric, a baseline of 4 is appropriate for 0 parameters. The description adds no parameter-specific meaning because there are none to explain.

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 ('Generate'), a specific resource ('fresh Ed25519 wallet'), and explicitly names the outputs (ICP principal and PKCS#8 PEM private key). It is clearly distinct from all siblings (check_cycles, claim_faucet_grant, deploy_site, deploy_upload_chunk, get_fuel_link), none of which relate to wallet creation.

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 to use it: when a new wallet is needed, and clarifies that no signup or on-chain registration is required, so it is the direct way to obtain a keypair. It does not explicitly name alternatives, but no sibling serves a similar purpose, so the context is sufficient.

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 no annotations provided, the description carries the full burden. It discloses the agent's controller role, the free-deploy funding mechanism, the ~1.4 MB decoded size limit, and the fallback tool. This goes well beyond a basic action statement and covers key side effects and constraints.

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 information-dense and front-loaded with the core action. No filler, no redundant restatement of schema fields, and every clause 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?

For a deployment tool with no output schema and no annotations, the description covers the full process, output URL, cost/funding, controller role, size limit, and alternative tool. Nothing essential for correct invocation 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful context: the agent parameter's consequence (becomes controller) and the files parameter's size constraint and chunking alternative. That extra semantic value justifies a 4.

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: 'Deploy a static website for an agent' and enumerates the concrete steps (create canister, install host, upload files, return URL). Clearly distinguishes from the sibling deploy_upload_chunk by naming it explicitly for larger files.

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 says 'use deploy_upload_chunk for larger files', giving a direct when-to-use vs alternative condition. Also provides the one-free-deploy policy and size limit, which clarify when this tool is the right choice.

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?

No annotations are present, so the description carries full disclosure burden. It discloses the stateful behavior clearly: chunks accumulate in order, and only the final chunk (is_last=true) assembles and publishes the file. It does not describe failure modes (e.g., out-of-order chunks or abandoned partial uploads) or auth requirements beyond the schema's agent ownership note, but the core behavioral contract is visible.

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, front-loaded with the purpose and selection condition before the essential workflow detail. Every clause 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?

Given 8 parameters fully documented in the schema and no output schema, the description covers the core chunked-upload workflow and ties it to the deploy_site sibling. The main gap is that it does not indicate what the tool returns or whether is_last produces a publish confirmation, but this is a minor omission for an otherwise well-specified stateful operation.

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%, giving a baseline of 3. The description adds relational meaning beyond individual parameter descriptions: it explains that chunk_index order matters ('Chunks are appended in order') and that is_last is the publication trigger. This cross-parameter semantics is genuinely useful and not directly inferable from the schema.

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 ('Upload'), resource ('one chunk of a large file to an already-deployed agent site'), and names the sibling deploy_site as the alternative for files that fit in a single call. An agent can clearly tell what this tool is for 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?

Explicitly provides the decision context: use this tool when files 'don't fit in a single deploy_site call', referencing the sibling directly. It also encodes the workflow rule — chunks are appended in order, with is_last triggering publication — so an agent knows exactly how to complete the operation.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add meaningful context: the payment is made by a human via Stripe and cycles land in the wallet. However, it leaves some behavioral details unspecified, such as link expiration, any wallet prerequisites, and whether generating the link has side effects beyond producing a payment link.

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 a single, front-loaded sentence that states the action first, then adds the payment mechanism and usage context. There is no filler, no restating of the schema, and every clause 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?

For a one-parameter tool with no output schema and no annotations, the description covers the essential context: what the link is, how the payment flow works, and when to use it. It could go slightly further by describing the return format or preconditions like needing a wallet first, but the description is close to complete for correct invocation.

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 even without parameter details in the description. The description only restates the principal concept and adds no format or constraint information beyond what the schema already provides. This is acceptable but not additive.

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 uses a specific verb-resource pair, 'Get the FirstKey Fuel payment link for a principal,' and explains the resulting flow: a human pays by card and cycles land in the agent's wallet. It also differentiates itself from the free faucet grant and deploy pool alternatives by calling this the 'sovereign refuel path' when those are exhausted.

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 explicitly states when to use this tool: 'when the free faucet grant or deploy pool is exhausted.' This gives the agent a concrete selection condition and implicitly maps to alternatives such as claim_faucet_grant and the deploy pool, making the decision boundary clear.

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 no annotations provided, the description carries the full behavioral burden and does it well: 'read-only', 'No tokens move', and 'execution happens in the agent's own wallet/canister' make side effects unambiguous. It stops short of caveats like quote expiry or slippage, but for a non-mutating quote tool the disclosure is strong.

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 front-loaded sentences cover purpose, side-effect safety, and token-format guidance in a logical order. Apart from the minor 'deepest on-chain DEX' color phrase, every sentence 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?

The description and fully self-documenting schema together cover invocation essentials: quote direction, non-mutating behavior, accepted token formats, and base-unit amounts. There is no output schema, so exact response shape is unspecified, but the return concept is intuitive and the fee-tier fallback is already documented in the parameter 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?

The schema already documents all four parameters with 100% coverage, so the baseline applies. The description adds limited value by narrating the pay/receive relationship and giving concrete symbol examples, but mostly it restates schema-level information rather than exposing new parameter constraints.

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 object: 'Get a live, read-only swap quote on ICPSwap' and defines exactly what is returned ('how much receive_token you would get for pay_amount of pay_token'). It clearly separates this pricing tool from the unrelated wallet/deploy/faucet 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?

It gives clear context: this prices intent only, no tokens move, and execution happens in the agent's own wallet/canister, which tells an agent when to call it and that it has no on-chain side effects. It does not explicitly name an alternative quote/execution tool, but none of the listed siblings competes with it.

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 no annotations, the description carries the burden and does well: it declares read-only ('no tokens move'), states that pricing is live on-chain, and explains the leg-chaining execution model. It stops short of quantifying cost/latency (relevant given the sibling check_cycles) or noting failure behavior when no route exists.

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?

One dense sentence followed by the read-only assurance and the sibling-routing rule, all front-loaded. Every clause carries information an agent needs; nothing is restated from the schema or name.

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 the description must characterize the return, and it does: 'returns the best route leg-by-leg' with chained quoted outputs. The intermediate token universe and the read-only guarantee round out what an agent needs to call 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 coverage is 100%, so the schema already documents fee, max_hops, pay_token, pay_amount, and receive_token in detail. The description adds the intermediate token set (ICP, ckUSDC, ckUSDT, ckBTC, ckETH) but no per-parameter semantics 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?

States a specific verb and resource ('route a swap intent across ICPSwap') and immediately scopes it: direct pool plus every two-hop path through named intermediates. It explicitly distinguishes itself from the sibling get_swap_quote, 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?

Gives an explicit alternative and the condition that selects it: 'Use this instead of get_swap_quote when a direct pool may be thin or missing.' This is a complete routing rule rather than an implied one.

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