Field Ops

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

With no annotations provided, the description carries the behavioral disclosure burden. It does reveal what information the tool exposes, including refusal reasons declared up front and pricing/guarantees, but it never states whether this is a read-only informational call, what the response structure looks like, or whether any side effects exist.

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 compact sentence that lists all key topics with no filler, repetition, or extraneous detail. Every listed item contributes to the agent's understanding of what the tool offers.

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, the description is largely complete: it names the main content categories an agent needs to know before invoking it. It could add the return format or explicitly state this is a read-only reference, but invocation itself is trivial, and the listed topics give enough context for selection.

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 baseline of 4 applies. The description does not need to explain parameter meanings, and it does not attempt to; the empty input schema is sufficient.

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 identifies the resource clearly—coverage areas, accepted question and shot types, refusal reasons, pricing, and guarantees—which sets it apart from siblings like check_feasibility or order. However, it lacks an explicit verb such as 'returns' or 'lists,' so it reads as a content label rather than a clear action statement.

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 explicit guidance on when to use this tool versus the sibling tools. The content implies it should be consulted to understand coverage, accepted types, and refusal reasons, but no direct context, exclusions, or alternative-routing cues are given.

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?

Since no annotations are provided, the description must disclose behavioral aspects. It mentions that it checks before paying thorough details of modes and refusal reasonage parts of behavior but lacks full transparency because it doesn't detail side effects (e.g., does it reserve anything?), whether it's read-only, or any rate limits. It adds value by describing the modes and that underspecified shots are refused, but misses a lot of behavioral context.

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 concise, using a single sentence to convey the core purpose and exceptions, followed by a terse enumeration of modes. Every word earns its place, front-loading the most important information (saving money) and avoiding 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?

Given the complexity (nested objects, multiple modes, 7 params) and the lack of an output schema, the description does a good job of covering the essential behaviors: how to use it, the modes, and the refusal mechanism. It doesn't describe return format, but that is expected since no output schema is given and the description states what it returns (price/lead time/refusal). It's a complete picture for an agent to call 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 schema already describes most parameters with 86% coverage, including descriptions for mode, shots, license, location, and declared_purpose. The description adds some context (e.g., modes, refusal of underspecified shots) but mainly repeats what the schema says. It does clarify that 'hours' is for watch, and 'shots' is for capture, which adds slight value 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 clearly states the tool's purpose: to check feasibility before paying, providing price and lead time, and refusal reason. It distinguishes itself from siblings by being the pre-payment check step, and it lists the three modes. It doesn't explicitly compare to siblings, but the context of 'call this first' implies it precedes 'order' and is distinct from 'capabilities' and 'mission_status'.

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 'Call this first' before paying, which indicates when to use it. It also implies that if feasibility is refused, you should not proceed to 'order'. It defines the modes and their parameter requirements, effectively distinguishing when to use each mode.

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 missing altogether, so the description carries the full behavioral burden. It does not mention side effects (likely read-only), error conditions, or what 'status' means in output. It doesn't disclose whether the tool is safe to call multiple times or if it requires additional context. For a tool that appears to be a query, the lack of any behavioral details is a significant 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?

The description is extremely concise – a single sentence. It is front-loaded with the key word 'Status.' However, it may be under-specified rather than elegantly concise; every word is meaningful but doesn't add enough context. It is not a tautology, but it lacks the depth needed for a well-rounded definition. The structure is fine, but the substance is thin.

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 the tool's simplicity (one parameter, no output schema, no annotations), the description is incomplete. It doesn't describe the return value format, possible status values, or error scenarios. It also doesn't hint at any dependencies (like a mission needing to exist). For an agent to correctly call this tool, it needs to know what to provide for 'mission' and what to expect back. The description is too sparse.

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 has one parameter, 'mission', of type string. Schema description coverage is 0%, meaning the property description is absent. The main description says 'Status of a placed mission,' which implies that the 'mission' parameter identifies the placed mission. This adds some semantic context (that a mission must be placed). However, it doesn't clarify the format of the mission identifier (e.g., ID, name) or any restrictions. With a single required parameter, the baseline is 3, and the description adds minimal meaning beyond the name, so a score of 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 'Status of a placed mission.' states a clear subject ('mission') and a state ('status'), but it lacks a specific verb. It doesn't clarify whether the tool retrieves, updates, or lists the status. The description is minimal but not a pure tautology; it does convey that the tool pertains to the status of a mission. Given the siblings (capabilities, check_feasibility, order), it's not clear how this tool differs from them beyond being about mission status.

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 provides no guidance on when to use this tool versus its siblings. It doesn't state when to check mission status, prerequisites (e.g., mission must be placed), or alternatives. Since 'order' and 'check_feasibility' likely relate to mission lifecycle, there is no explicit differentiation. The only hint is the word 'placed,' implying it's for existing missions, but that's not made 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 carries the full behavioral burden. It discloses one conditional behavior, returning a payment requirement when proof is absent, but leaves undefined what proof means, what happens when proof is supplied, and any side effects, permissions, or failure modes. This is too thin for an ordering action.

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, and the main action is front-loaded. However, for an 8-parameter tool with no schema descriptions, the terseness crosses from concise into under-specified.

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?

Despite 8 parameters, nested objects, no output schema, and no annotations, the description provides only a one-line effect and a single conditional return. An agent would not know how to construct a valid request or interpret the payment requirement, so the definition is not complete enough 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?

The input schema has 8 parameters at 0% description coverage, and the description adds almost nothing about them. It does not explain mode, hours, shots, license, deadline, location, questions, or declared_purpose; 'proof' is mentioned but is not even a declared parameter, which actively complicates parameter mapping.

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?

Opens with a specific verb and object ('Places an order') and adds a distinguishing conditional outcome about payment requirements. It does not define the domain of the order, but it is clear enough to separate from siblings like check_feasibility or mission_status.

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 guidance on when to use this tool versus check_feasibility, capabilities, or mission_status, nor on prerequisites such as proof. The 'when no proof is supplied' clause hints at a payment flow but never states when ordering is appropriate or what alternatives should be used first.

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