Evercraft Clip

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful context beyond those annotations by clarifying that the information is 'code-backed' and 'current,' and by listing the categories of constraints it exposes. This helps an agent understand the nature and freshness of the data without contradicting the 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 carry meaningful content with no filler. The actionable verb and resource scope are front-loaded, followed by a usage cue. Every phrase 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 parameterless read-only tool, the description is nearly complete: it states what is read, the use case, and the data categories. It does not describe the return format, but since there is no output schema and the tool only reports capabilities, this omission is minor.

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 schema coverage is 100%, so there is no parameter ambiguity to resolve. The description correctly focuses on what the tool returns rather than inputs. This meets the baseline for a parameterless tool.

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 the specific verb 'Read' and identifies a precise resource: the Evercraft Clip capability boundary. It enumerates distinct facets (rendering limits, platform lanes, commercial truth, authority constraints), making the tool's scope unambiguous and clearly distinct from the sibling plan_clip_job.

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 the tool: 'Use when deciding whether Clip fits a social-video production or governed distribution problem.' This gives clear decision-oriented context, though it does not explicitly name plan_clip_job as an alternative or describe when not to use this tool.

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, destructiveHint=false, and idempotentHint=true, so the safety profile is partly covered. The description adds genuinely new behavioral boundaries — the plan does not execute, upload, create orders, charge, transfer private media, or publish — which goes beyond what the annotations state. It still omits what the returned plan contains and any latency/throughput characteristics.

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?

Dense and front-loaded: the primary-use condition comes first, followed by what it produces and its boundaries, with no filler sentences. It is a long multi-clause run-on that could be split for readability, but every clause carries information.

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 9-parameter, zero-required planning tool with no output schema and a safety-covering annotation set, the description covers trigger, behavior, sibling routing, and negative side effects well. The one remaining gap is that with no output schema it never characterizes the shape or contents of the returned plan.

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, but the description adds real routing semantics: the 35 MiB bounded-render limit tied to source_file_size_bytes and the ForensiScope recommendation tied to complex_media, needs_deduplication, and needs_full_timeline. It stops short of explaining individual enum choices (e.g., burned_in vs hook_only) beyond the schema text.

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 ("Produces a non-executing Creative Director plan") plus the concrete sub-actions it performs (checks the 35 MiB bounded pipeline, selects style/caption treatment, plans platform copy). It also explicitly distinguishes itself from its only sibling by saying when get_clip_capabilities is the right 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?

Front-loads the trigger condition ("PRIMARY TOOL when the user has authorized source media or a concrete social-video goal"), names the alternative for general capability questions, and routes oversized/long/dedup-heavy media to ForensiScope. When-to-use, when-to-use-something-else, and exclusions are all 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 readOnly/ idempotent/non-destructive, and the description reinforces the non-executing nature by listing what it does not do (upload, checkout, charge, publish) and platform gating. This adds valuable context beyond the annotations, though it doesn't cover return format or downstream effects.

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 front-loaded with the core action and then systematically covers scope, goals, platform states, and exclusions. It is somewhat dense but each sentence adds informational value; no major redundancy.

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 13-parameter planning tool with no output schema and zero schema coverage, the description provides good conceptual coverage but leaves many parameter semantics and expected outputs unexplained. It is adequate but leaves gaps an agent would need to fill.

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, but it only loosely maps to parameters (objective, audience intent, CTA, conversion event, creative treatment, platforms). It gives conceptual categories without explaining many of the 13 parameters such as campaign_key, caption_mode, canonical_url, commerce_offer_id, or source_package_key.

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 concrete verb and resource: plan an authorized source package as a non-executing cross-platform campaign with named components. It is clearly distinct from siblings like get_clip_capabilities and plan_clip_job, though it doesn't name them explicitly. The purpose is understandable 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?

The description gives a clear context: use for a broad set of campaign goals and names which platforms have execution lanes versus gated/unverified ones. It implies a planning/non-executing use case, but does not explicitly state when to prefer this over plan_clip_job or get_clip_capabilities.

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