Critique a company’s brand from its public website and an optional public document. Sigil returns positioning, visual identity, voice, a brand score, prioritized changes, and a link to the full Read; it does not design logos, generate brand books, or access private company systems.
Scored across 2 tools
start_read initiates a brand critique and returns an id, while check_read retrieves the status or result of that specific read. Their purposes are clearly distinct and complementary, with no overlap.
Both tools follow the same verb_noun pattern (start_read, check_read) using snake_case consistently. The noun 'read' is used uniformly, making the naming predictable.
The server provides only two tools, which is thin for general MCP servers but arguably sufficient for a single-purpose asynchronous service. The 1-2 tool range is borderline per the rubric, earning a middle score.
The tools cover the core async workflow: start a read and check its status/result. Minor gaps exist (e.g., listing past reads or cancelling), but these are not essential for the primary use case.
Where a Brand Read stands. When it is ready, the full result as text and a link to it on Sigil's site.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The id start returned. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds genuine context beyond them: the return payload is state-dependent, giving status before completion and full result text plus a site link once ready. It does not mention failure/expired-read states, which keeps it from a 5.
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, zero filler, and the core concept (current state) is front-loaded before the ready-state payoff. Nothing could be removed without losing 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?
There is no output schema, so the description must carry return-value semantics, and it does describe both the in-progress and completed response shapes. It omits error/expiry handling and any indication of what the status values look like, which is the remaining 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?
Only one parameter exists and the schema documents it fully (100% coverage, with its own description). With the schema doing the heavy lifting, the baseline is 3; the description adds no extra meaning about the id's provenance beyond what the schema field note already supplies.
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 names the resource ('a Brand Read') and describes the operation's outcome ('Where a Brand Read stands', with the full result and a link once ready), so an agent knows this is a status/result-retrieval call. It does not explicitly name the sibling start_read, though the phrasing implies this follows a start, so it stops just short of full sibling differentiation.
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: 'Where a Brand Read stands' plus 'When it is ready' suggests polling after starting a read, but the description never states when to call this versus start_read, nor any polling cadence or retry guidance. Adequate for an agent that already understands the start/poll pattern, thin otherwise.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sigil's critique of a company's current brand from its website and, optionally, one document (a pitch deck, memo or product brief). Use it when someone wants feedback on their brand, positioning, messaging, website or visual identity. It returns a brand score out of 100, a verdict, six scored dimensions, what the brand says against what the business is, positioning, visual identity and voice notes, a one-line brand idea and the changes to make first.
Starts the work and returns an id. It usually takes a few minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| site | Yes | The company's public website, such as acme.com. | |
| document_url | No | A public link to one document about the business: PDF, PowerPoint, Word, Markdown or text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (non-read-only, non-destructive, non-idempotent, open-world), so the description adds real value by disclosing the async contract: it returns an id and 'usually takes a few minutes.' It also enumerates the eventual output, which matters because there is no output schema.
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 paragraphs, front-loaded with what it does, followed by the async caveat. The return-value enumeration is long but defensible given there is no output schema.
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 an async job-starting tool with no output schema and fully documented params, the description covers inputs, latency, and eventual returns. The one gap is not stating that check_read retrieves the result, though the sibling name makes that inferrable.
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 the baseline is 3. The description adds modest meaning by noting the document is optional and giving examples (pitch deck, memo, product brief) beyond the schema's file-type list, but nothing about URL format or limits.
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?
Names a specific verb and resource ('Sigil's critique of a company's current brand') and the inputs it works from. It is clearly distinguishable from the polling sibling check_read by the 'Starts the work and returns an id' sentence, though it doesn't name check_read 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?
Gives explicit trigger conditions: 'Use it when someone wants feedback on their brand, positioning, messaging, website or visual identity.' No exclusions are stated, and it never tells the agent that results must be fetched via check_read, which is the natural follow-up.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_readstart_read
Add one secure layer between your agents and this server.