CodexImmortal

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered; the description adds real value by disclosing the four verification dimensions performed. It stops short of saying what happens on a failed verification (exception vs. boolean verdict) or what the response contains, which is the remaining behavioral 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?

One sentence, front-loaded with the action and resource, followed by the concrete list of checked properties. Zero filler and no repetition of structured fields.

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 read tool with annotations covering safety and a fully documented schema, the core is covered. However, with no output schema present, the description should state what verification yields (pass/fail, error list) and how failures surface, which it does not.

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 parameter is fully documented in the schema as 'Attestation ID or sha256 content hash'. The description mentions content hash only as a verified artifact, not as an accepted input form, so it adds no meaning beyond the schema. 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 (Verify) and resource (Codex Immortal attestation record), then enumerates exactly what aspects are checked: content hash, signature, timestamp, ledger inclusion proof. This clearly separates it from all siblings, which handle catalog, purchase, quote, and scan 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?

Usage is implied by the tool's name and the fact that it verifies an attestation, but the description never states when to call it versus alternatives, nor any precondition such as 'use after retrieving an attestation' or 'call before trusting a record'. No exclusions or routing guidance are present.

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 and idempotentHint, so the safety profile is covered. The description adds value by disclosing the returned sections (pricing, SLA, refund/dispute terms, evidence, validation status), but says nothing about failure behavior for an unknown offer_id or about any auth/tiering requirements.

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 sentence, front-loaded with the verb and scope, with the returned fields listed after a colon. Efficient, though "ERC-8004-shaped" is domain jargon that adds little for an agent unfamiliar with the standard.

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 with no output schema, the description does a reasonable job of previewing the response shape. It is incomplete on the practical prerequisites: how to obtain a valid offer_id and what happens when it is not found.

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 0%, so the single offer_id parameter is entirely undocumented in the schema, and the description does not compensate — it never says where an offer_id comes from or whether it corresponds to a product ID. The phrase "one product" versus a parameter named offer_id even leaves a small ambiguity about identifier type.

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?

Specific verb ("Get") plus a clearly bounded resource (the full service offer for one product), and it enumerates the payload sections an agent gets back. It does not explicitly distinguish itself from the sibling codex_catalog_list, but the singular "one product" scope implicitly separates it from a listing call.

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?

No when-to-use or when-not-to-use guidance, and no sibling is named as an alternative despite codex_catalog_list and codex_quote_request being obvious neighbors. The agent must infer that this is the detail-fetch counterpart to a catalog listing.

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 readOnlyHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds genuine value by telling the agent what information the records contain (pricing basis, denied capabilities, validation status), but says nothing about result volume, pagination, or how 'denied capabilities' are represented.

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 tight sentence that front-loads the verb and resource and packs the returned attributes efficiently. The trailing list of attributes is dense but each item carries information, so nothing is wasted.

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 catalog listing this is close to adequate: the annotations cover the safety profile and the description enumerates what each record contains. However, the sole filter parameter is undocumented in both schema and description, and there is no hint about result size or pagination, leaving a real gap for an agent that needs to enumerate the full catalog.

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 single parameter 'category' has an enum and a default of 'all', but zero schema description coverage, and the description never mentions filtering by category at all. With coverage at 0% on a non-trivial enum parameter, the description should compensate and does not; an agent cannot tell whether 'category' scopes the listing or is merely a tag.

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 ('List') and resource ('Codex Immortal products and services') and even enumerates the attributes surfaced (pricing basis, capabilities, denied capabilities, validation status). It implicitly distinguishes itself from the singular sibling codex_catalog_get_product, though it never names that sibling or states the distinction explicitly.

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 guidance, no when-not-to-use guidance, and no mention of alternatives such as codex_catalog_get_product for single-item lookups or codex_quote_request for pricing. The agent is left to infer all routing from the tool name alone.

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 readOnlyHint=true, and the description reinforces this by explicitly disclaiming payment execution, card charges, and fund movement. It adds real value beyond the annotation by explaining the approval workflow and the single-use, exact-match TGA prerequisite for downstream execution. It stops short of describing rate limits or how the draft payload is keyed to a session.

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: purpose and return artifact first, then the safety boundary. Nothing repeats structured data and 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?

No output schema exists, so it is important that the description names the return value, which it does ('AP2/x402 checkout payload draft'). The safety boundary is also covered, making this sufficient for a non-destructive preparation tool; only the undocumented parameters keep it from being 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 0% and the description never mentions offer_id, quantity, or currency. Only a loose hint exists that the item is a 'catalog item', leaving the agent to infer that offer_id is a catalog offer identifier and that quantity/currency shape the proposal. With three undocumented parameters, this is a clear gap.

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 ('Prepare a purchase proposal for a catalog item') and names the concrete artifact returned ('AP2/x402 checkout payload draft'). It is clearly a pre-payment step, but it never distinguishes itself from the sibling codex_quote_request, which sounds like a neighbouring operation an agent could easily 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?

The description implies usage via 'for human approval' and 'execution happens only through the isolated financial connector gateway', which tells the agent this is the pre-execution stage. However, it gives no explicit when-to-use versus codex_quote_request or codex_catalog_get_product, so routing between siblings is left 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?

The description adds real value beyond the single readOnlyHint annotation by disclosing the response shape: an RFQ reference plus an expected response time, which is important because there is no output schema. It does not say whether the request persists state or is queued for human review, whether it is idempotent or can be withdrawn, or what auth/approval is needed — and 'request... returns an RFQ reference' sits in mild tension with readOnlyHint=true, though it can be read as a non-mutating information request rather than a write to an existing resource.

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 with no waste, and the purpose is front-loaded ahead of the return-value sentence. Slightly more content (parameter meaning or a sibling pointer) could have used the remaining space rather than being absent.

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 tool with two required inputs, no output schema, no annotations beyond readOnlyHint, and zero schema description coverage, the definition is thin: an agent knows what to ask for and roughly what comes back, but not what to put in offer_id or buyer_description, nor what happens after the request is submitted.

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 0%, so the description must carry the burden and it largely does not. Only 'volume' is echoed loosely; offer_id (which catalog object identifies the offer?) and buyer_description (format, length, what to include, whether it drives the quote) are completely unexplained, and the required-vs-optional distinction is invisible to the reader.

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+resource ('Request a quote') and narrows scope to 'volume, enterprise, or custom-scope engagements', which tells an agent this is not the standard purchase path. It never names a sibling tool (e.g. codex_purchase_initiate), so differentiation is left to inference rather than stated.

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 implied by the qualified scope ('volume, enterprise, or custom-scope'), suggesting this is for non-standard deals rather than ordinary catalog purchases. There is no explicit when-to-use/when-not guidance, no prerequisites, and no pointer to codex_catalog_get_product for the offer_id or to codex_purchase_initiate for a ready-to-buy flow.

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 destructiveHint=false, and the description reinforces this with "defensive and read-only by design" while adding genuinely new behavior: live-scope requests are gated to a human before execution. That routing/gating detail is exactly the kind of context annotations cannot convey. It stops short of describing turnaround or how results are delivered.

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 purpose, then safety posture, then the gating rule. Nothing is wasted, though the parenthetical category list is slightly compressed and could read as fragmentary.

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 request tool with no output schema and no annotations covering outcomes, the description omits what happens after submission — whether the scan is asynchronous, what identifier is returned, or how findings are retrieved. Given the human-gate behavior it describes, an agent would reasonably want to know the request's lifecycle, and that 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 description coverage is 0%, so the description must carry parameter meaning, and it only partially does. It names the hunt categories (matching the scan_type enum) and alludes to the environment parameter via the live-scope gating sentence, but never explains the test/live distinction itself or what a good scope_description looks like. The enum values are already in the schema, so listing them adds limited value beyond the HNDL expansion.

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-plus-resource ("Request an autonomous threat-hunt scan") and enumerates the covered hunt categories, so the agent knows exactly what capability is being invoked. It doesn't explicitly contrast itself with the catalog/purchase/quote/attestation siblings, but the domain gap is obvious enough from the wording.

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 implied rather than stated: the agent can infer this is the tool for initiating threat hunts, and the note about live-scope scans routing to a human gate gives a useful precondition. There is no explicit when-not guidance and no reference to an alternative tool for related tasks.

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