ForensiScope by Evercraft

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

Annotations already establish the read-only, idempotent, non-destructive profile, and the description adds the conditional clause 'when determinable,' indicating that the price may not always be returned. It also states that both a route and price are outputs, which is helpful given there is no output schema. No annotation contradiction 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?

The definition is a single sentence plus a redundant but harmless 'Read-only.' The core action, target resource, route set, and conditional price output are all packed efficiently and front-loaded. There is no filler or repetition beyond the annotation-consistent read-only label.

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 specifies the expected outputs and the main precondition, but it does not state what happens if both optional parameters are absent or when determinability fails. Because there is no output schema, the agent is left to guess the edge-case behavior. For a two-parameter read-only tool with strong annotations, this is a moderate but notable 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?

With schema description coverage at 0%, the description carries the burden of explaining size_bytes and duration_seconds. It maps them to 'media file size and/or duration' and clarifies that either or both can be supplied, which goes beyond the bare schema names and constraints. It does not specify units or the behavior when neither parameter is provided, but the parameter names already imply bytes and seconds.

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 and object: 'return the correct ForensiScope route' and enumerates all four possible routes, leaving no ambiguity about what the tool produces. It also distinguishes itself from siblings such as get_forensiscope_pricing and prepare_forensiscope_handoff by describing classification as the core purpose.

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 phrase 'Given known media file size and/or duration' clearly states the input condition that triggers use of this tool. It does not explicitly mention when not to use it or direct the agent to get_forensiscope_pricing for pricing-only needs, but the description makes the classification-for-route use case obvious.

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 mark this as read-only, idempotent, and non-destructive; the description adds useful context by specifying what the tool will disclose (current boundaries, supported outputs, unsupported claims). This goes beyond the annotations without contradicting them.

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 with each phrase contributing a distinct content category. It earns its place, though the phrase 'machine-facing' is slightly redundant and the sentence reads more like an instruction than a behavioral description.

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 capability-introspection tool, the description sufficiently conveys the scope of return content. There is no output schema, and the description does not describe the exact return shape, but the listed categories are enough for a basic agent to select and invoke it safely.

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 100% schema coverage, which establishes a baseline of 4. There are no parameter semantics for the description to add, and it does not need to compensate for missing schema documentation.

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 clear verb (Describe) with a specific resource (ForensiScope) and names the content areas it covers: routing capabilities, current boundaries, supported outputs, and unsupported claims. It is distinguishable from the pricing and handoff siblings, though it does not explicitly contrast itself with classify_media_route.

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 guidance is provided. The description does not say to call this before routing or how it differs from classify_media_route, get_forensiscope_pricing, or prepare_forensiscope_handoff, leaving the agent to infer the selection logic from names 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the specific behavioral guarantee 'creates no checkout', which is not in the annotations and clarifies there is no side effect like initiating a purchase. It also says 'current published', implying up-to-date data. 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, front-loaded with the primary purpose and a clear behavioral note. No wasted words, no redundancy with annotations, and the key information is immediately accessible.

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 read-only tool with no parameters and no output schema, the description covers the essential purpose and the key behavior (no checkout). It does not specify the return format, but for a pricing lookup that may be self-evident. It is adequate for an agent to decide whether to call 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 is trivially complete (100% coverage). The description adds no parameter details, but none are needed. Per the baseline for 0-parameter tools, a score of 4 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 tool returns current published duration pricing and self-service/assisted-ingest boundaries. It is specific about the resource (pricing) and distinct from siblings: get_forensiscope_capabilities covers capabilities, classify_media_route covers classification, and prepare_forensiscope_handoff covers handoff. An agent can immediately tell this is the pricing lookup.

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 when pricing or ingest-boundary information is needed, but it does not explicitly state when to use this tool over alternatives or mention exclusions. There is no 'use this when...' or 'instead of...' guidance, leaving the agent to infer from the tool's name and content.

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, idempotentHint=true, and destructiveHint=false. Beyond that, the description adds a useful negative side-effect list ('does not upload media, attest rights, create checkout, charge, or start analysis') and identifies the return artifact as a tagged URL. This is meaningful context that goes beyond the annotations without contradicting them.

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 fluff. The core action and return value are front-loaded, the use-case list is compact, and the negative constraints are delivered in one efficient clause. Nothing is repeated from the schema or annotations.

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 two-parameter tool, the description covers the intent categories, the return type, and side-effect negation. With no output schema, it would be more complete if it explained what 'tagged' means and what the 'source' parameter contributes, but the description is otherwise sufficient for basic 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 0%, so the description must compensate. It does map the intent enum values to natural-language use cases ('surveillance' to 'surveillance review', 'compare' to 'recording comparison', etc.), which helps agents pick an intent. However, the 'source' parameter is completely undocumented, and the meaning of 'tagged' is never tied to parameters or behavior.

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 resource: 'Return a tagged ForensiScope URL', then enumerates six concrete use cases (overflow, long-form analysis, surveillance review, recording comparison, incident timeline, pricing). It also differentiates itself from siblings by explicitly listing what it does not do: 'Does not upload media, attest rights, create checkout, charge, or start analysis.' This makes the tool's role clear and separable from classify_media_route and get_forensiscope_pricing.

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 gives clear context for when to use this tool by listing eligible intents and by stating non-actions that effectively say when not to use it. However, it never explicitly names alternatives or gives an exclusion like 'for classification use classify_media_route', so it stops short of a full 5.

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