Eous

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

The readOnlyHint annotation already declares this is a safe read operation. The description adds content scope—what Eous is and does not do—and the instruction to read before submitting, which is behavioral guidance. It does not contradict annotations and provides appropriate context for an informational tool, though it omits specifics about output format.

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 communicates purpose, scope, and usage in under 25 words. Every phrase earns its place—'what Eous is', 'what it does and does not do', 'how to work with Forged Lucidity', and 'Read this before submitting'—with 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?

For a zero-parameter informational tool with no output schema, the description covers purpose, scope, and usage guidance. It does not describe the return format, but that is a minor omission given the tool's simple nature and the readOnly annotation. The description is sufficient for an agent to know when and why to invoke it.

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, so the schema imposes no burden. Baseline for 0 params is 4; the description correctly avoids any parameter-related information since none exist. There is nothing more needed for parameter semantics.

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 the tool's purpose as providing an overview of Eous ('what Eous is, what it does and does not do') and guidance on working with Forged Lucidity. It clearly distinguishes itself from siblings like check_status or submit_claim by being an informational reference rather than an action, and the 'Read this before submitting' hint reinforces its role as a prerequisite.

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 instructs the agent to read this before submitting, giving a clear when-to-use directive relative to sibling submit_claim. It also provides contextual guidance on how to work with Forged Lucidity, implying this tool should be consulted for background before other actions. It does not name alternatives explicitly but the usage context is 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 readOnlyHint=true, the safety profile is already clear. The description adds meaningful behavioral context by stating that the answer is only shown once released, alerting the agent to a conditional availability that the schema and annotations do not convey. No contradiction with 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 short sentences with no filler. The core action and key conditional behavior are immediately visible, and the single-sentence param guidance is handled in the schema.

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-parameter read-only lookup with an output schema, this description is complete. It conveys what the tool does, what it takes, and the release-based constraint that affects expected results.

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 documents the receipt_id format and its provenance from submit_claim or contact_us. The description reinforces that the lookup is 'by its receipt ID' but adds no semantic detail beyond 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?

The description states a specific verb ('Look up') and resource ('a claim or a message') with a clear identifier ('receipt ID'). It is distinct from siblings like submit_claim and contact_us, which create items rather than retrieve statuses.

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 the appropriate context: after submitting a claim or message via submit_claim or contact_us, use this tool to look it up by receipt ID. It also conditionally notes that the answer appears only once released, though it does not explicitly name exclusion cases or alternatives beyond that implied 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 are sparse (no meaningful hints beyond non-readonly), so the description carries the burden. It usefully discloses that a person reads every message and that replies are not instant, and it promises a receipt ID. This adds behavioral context beyond the schema without contradicting 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 tight sentences with no filler. The core action and message kinds are front-loaded, followed by the key output (receipt ID) and the important human-review latency caveat.

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 contact form with full schema coverage and an output schema, the description covers the essential behavior: what to send, what you get back, and the non-instant nature of replies. The only notable gap is explicit guidance on when to choose a sibling tool instead.

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 all four parameters thoroughly. The description repeats the enum values in prose but does not add new semantic detail about message formats, email behavior, or acknowledgment requirements.

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 action ('send') and resource ('a message'), and enumerates the accepted kinds: question, scoping, partnership, or press. This clearly differentiates it from siblings like check_status and submit_claim, which 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 implies when to use the tool—for general questions and partnership/press outreach—but never explicitly contrasts it with sibling tools. It does not say 'for claims, use submit_claim' or 'to check progress, use check_status', leaving the routing partly 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 are all false (readOnly, openWorld, idempotent, destructive), so the description carries the burden of disclosing side effects. It explicitly states 'A person reviews every submission before any answer is released; nothing is instant,' which is meaningful beyond the annotations. It also mentions a receipt ID, indicating a submission rather than an immediate answer. No contradiction with 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 sentences, zero waste. The core action and key behavioral caveat are front-loaded. Every phrase adds value: the action, the receipt ID, and the human-review/non-instant warning. No redundancy or fluff.

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 covers the essential action, the asynchronous nature, and the receipt ID. An output schema exists, so return values are already specified. For a submission tool with clear annotations and schema, nothing critical is missing 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?

Schema description coverage is 100%, meaning each parameter has a description in the schema. The tool description itself does not add parameter-specific detail, but the schema fully documents them, including the required 'acknowledge' boolean and optional fields. Baseline of 3 is appropriate given high 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 ('send'), a clear resource ('one claim'), and the purpose ('checked at its primary source and graded'). It also distinguishes itself from sibling tools: check_status is for status, contact_us for contact, and about_eous for info. No ambiguity.

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 clearly indicates this tool is for submitting a claim, and the non-instant, human-review nature sets expectations. It does not explicitly name alternatives or provide when-not-to-use guidance, but the sibling names make the use case obvious. A minor gap: no mention that check_status should be used after submission.

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