kavel-mcp

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the useful context that this targets in-flight generations, but omits key behavioral details such as whether the call blocks, how often to poll, or whether results expire.

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?

A single front-loaded sentence with no filler; every clause carries meaning. Appropriate size for a one-parameter lookup tool.

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?

With no output schema, the description should carry more of the return-value burden. It does not say what a pending versus completed response looks like, which is the central question for a polling tool.

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 schema already documents that task_id comes from generate_kavel_image. The description adds nothing beyond the schema for this single parameter, so the 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 (get) and resource (the result of a Kavel generation) with a qualifying condition ('that was still rendering'). This differentiates it from generate_kavel_image, though it never names that sibling 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?

The phrase 'that was still rendering' implies the polling-after-generate pattern, so usage is inferable. However, it gives no explicit when-not guidance, no mention of how to obtain the task_id beyond the schema, and no statement about what to do if the generation is still pending.

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 openWorldHint=false. The description adds real value beyond that: it describes the return payload (slug, required input type, kavel.ai page) and discloses the important behavior that video tools cannot be executed here but open externally.

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, front-loaded with what the tool does, followed by return shape and the run/open distinction. No filler or repetition.

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?

With no output schema, the description compensates by spelling out the returned fields (slug, input requirement, kavel.ai page) and the image-vs-video execution path. An agent has everything needed to call it and act on 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%, so both parameters are already documented, and the hub enum is self-explanatory. The description only reinforces their intent ('photo or just text', search-oriented query) without adding syntax or format detail, so the baseline 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?

States a specific verb ('Search') and resource ('Kavel's AI photo and video effects') and immediately gives concrete examples (hairstyle changer, figurine, yearbook photo). It also distinguishes itself from the sibling generate_kavel_image by clarifying that searching finds tools while generating runs them.

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 routes the agent: image tools can be run via generate_kavel_image, video tools open on kavel.ai. That is a clear use-context, though it doesn't compare against check_kavel_generation or get_kavel_balance, and gives no explicit when-not-to-use.

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 only declare the mutation/safety profile; the description adds the operationally critical facts beyond them: it spends credits from the linked account, typically completes within a minute, and otherwise returns a task_id for async polling. Those are exactly the traits an agent needs before invoking a metered mutation.

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?

Front-loads the core action, then layers the tool/photo requirements, cost, and async behavior in tight sentences with no filler. Every clause carries decision-relevant 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 metered, potentially async generation tool with no output schema, the description covers cost, expected latency, the async escape hatch, and where the tool slug originates — everything needed to call it correctly and interpret the result.

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%, so baseline is 3, but the description genuinely adds meaning beyond the schema: `tool` consumes a slug from find_kavel_tool and reinterprets `prompt` as the user's extra details rather than a standalone prompt. The photos-vs-image_urls distinction is reinforced too. It stops short of full coverage of aspect_ratio behavior, so not a 5.

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 ('Create an image from a prompt, or edit the user's photo') scoped to the Kavel account, which cleanly separates it from find_kavel_tool (lookup) and check_kavel_generation (polling). An agent can identify the tool's job 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?

Gives explicit routing: take `tool` from find_kavel_tool, require a photo for photo tools (attachment in `photos` or link in `image_urls`), and fall back to check_kavel_generation when a task_id is returned. Both the when-to-use and the sibling handoffs are spelled out.

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 openWorldHint=false, so the agent knows this is a safe, non-mutating read against a specific external account. The description adds no further behavioral context such as whether the account must be linked first, error behavior when unlinked, or units/currency of the credits.

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?

A single sentence, front-loaded with the resource and framed around the value returned, with no wasted words. The interrogative phrasing is slightly indirect for a tool description but remains immediately parseable.

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?

With no parameters, no output schema, and annotations covering the safety profile, the description carries only the burden of stating what comes back, which it does ('how many credits are left'). Minor gaps remain around account-linkage prerequisites and the exact return form, but nothing essential to correct invocation 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?

The tool takes zero parameters, so there is no parameter semantics to document; the baseline for a no-parameter tool is 4. Nothing in the description contradicts or muddies the empty 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 resource (Kavel credit balance) and what is returned (credits left on the linked account), so an agent knows exactly what this tool retrieves. It does not, however, differentiate itself from siblings like check_kavel_generation or find_kavel_tool, leaving the agent to infer the boundary from names alone.

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 statement of when to use this tool versus the siblings (check_kavel_generation, find_kavel_tool, generate_kavel_image), nor any prerequisite or context for invoking it. The purpose is simple enough that implied usage is obvious, but no explicit guidance is offered.

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