Sigil

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds meaningful context about the two-phase return (status, then full text and link when ready), but omits what the possible status values are and whether repeated calls are expected.

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 core purpose is front-loaded. The sentence fragments make it slightly clipped and the readiness behavior could be ordered more clearly, but nothing is wasted.

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 must carry return-value information, and it does sketch the return (status plus full text and link when ready). However, it leaves out the status vocabulary and polling expectations, which an agent needs to use this correctly in a review-then-check workflow.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the id field. The description adds nothing about the id beyond what the schema says ('The id start returned'), 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?

The description states the resource (a Brand review) and what it returns (status, then full result text plus a site link), so the operation is identifiable as a status/result fetch. It doesn't explicitly distinguish itself from the sibling start_read, which is the tool that produces the id this one consumes.

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?

Usage is only implied: the wording 'Where a Brand review stands' and 'When it is ready' hints at polling until completion, but there is no explicit when-to-use, no guidance on how often to poll versus when to stop, and no mention of the start_read sibling as the predecessor.

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 the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds genuinely new behavioral context: the call starts asynchronous work, returns only an id, and 'usually takes a few minutes.' It does not state what the id is used for or any cost/rate limits, so it is strong but not complete.

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 purpose and the trigger condition are front-loaded, and the async/id/timing note is a tight closing line. The long enumeration of return contents is verbose, but since there is no output schema it earns most of its space.

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 usefully inventories what comes back (score out of 100, verdict, six dimensions, notes, one-line idea, first changes). The one real omission is the async follow-up loop — it says an id is returned but not that the result must be fetched via check_read.

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. The description still adds meaning by characterizing document_url as 'one document (a pitch deck, memo or product brief)' and framing it as optional relative to the required site, which conveys the intent of the parameter beyond the schema's format list.

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 ('Sigil's review of a company's current brand from its website and, optionally, one document') and clarifies the async model with 'Starts the work and returns an id.' That framing cleanly separates it from the check_read sibling, which is the natural polling counterpart.

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?

'Use it when someone wants feedback on their brand, positioning, messaging, website or visual identity' gives an explicit trigger condition and a concrete list of intents. It stops short of naming check_read as the follow-up step or stating when not to use it, so it is clear context rather than full routing.

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