See what any amount really looks like: weight, volume, pile size and a true-scale photo.
Scored across 2 tools
The two tools have clearly distinct purposes: get_page retrieves an existing page, while visualize generates a new visualization. An agent can easily tell them apart based on intent, with no risk of misselection.
get_page follows a verb_noun pattern, but visualize is a bare verb. This mixed convention is noticeable and reduces predictability, though both names remain readable.
With only two tools, the surface feels thin for a server that could support discovery or listing. While the core operations are present, the count is borderline low.
The server covers creation (visualize) and retrieval (get_page) of pages, which is the core lifecycle. However, there is no way to list or search existing pages, which is a minor gap that agents might need to work around.
Fetch the numbers and photo for an existing VisualizeVolume page by its URL or slug. Free; no AI call.
| Name | Required | Description | Default |
|---|---|---|---|
| page | Yes | Page URL or slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuinely useful behavior: the operation is free and performs no AI call, which is a cost/latency characteristic not expressed anywhere in structured fields, and it sketches the return payload ('numbers and photo').
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 filler; the verb+resource comes first and the cost note follows. 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 one-parameter read with no output schema, the description covers what is fetched ('numbers and photo') and the cost model. Minor gaps remain: it doesn't say what happens for a nonexistent page or the exact response shape, but nothing essential blocks a correct call.
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 single parameter's 'Page URL or slug' description already covers both accepted forms, which is exactly what the tool description repeats. Baseline 3 is appropriate since the schema does the work.
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 verb ('Fetch') and resource ('the numbers and photo for an existing VisualizeVolume page'), and the input route (URL or slug) is named. It stops short of explicitly distinguishing itself from the sibling 'visualize', though 'no AI call' hints at the difference.
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?
'Existing' page and 'Free; no AI call' imply this is the cheap retrieval path versus the generative sibling, but the description never names 'visualize' or states when not to use this tool. Usage is only implied, not spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Answer 'how big is it really?' for any amount or number of things: '50 grams of sugar', '1 cubic yard of mulch', '1,000 ducks', 'how many pickles weigh as much as a person', 'chicken vs duck vs ostrich'. Returns volume, weight, kitchen measures, pile or group size, a plain-language description ('about the size of a golf ball'), a true-to-scale photo URL and the page URL to cite.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question in plain words. | |
| make_photo | No | Create the photo if it doesn't exist yet (needs an API key). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and openWorldHint=true, which is consistent with the optional photo-creation side effect, and the description does not contradict them. It adds useful output context (volume, weight, kitchen measures, photo and page URLs to cite) but does not mention the API-key requirement or that photo generation can mutate server state — that detail lives only in the 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?
A single front-loaded sentence pairing the purpose with illustrative examples; the return-value list is compact and informative. The example string is long but each clause maps to a supported query type rather than padding.
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 carries the return-value burden and does so thoroughly (measures, plain-language size, photo URL, citation page URL). The gaps are minor: no disclosure of the API-key/auth need for photos and no indication of latency or failure behavior when a photo cannot be made.
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 enriches the query parameter by demonstrating the accepted input range: quantities with units, counts of objects, inverse questions, and A-vs-B comparisons. That goes beyond the schema's terse 'The question in plain words.'
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 capability — answering 'how big is it really?' for any amount or number of things — and backs it with concrete query archetypes ('50 grams of sugar', '1,000 ducks', 'chicken vs duck vs ostrich'). It never mentions the sibling get_page or clarifies the boundary between them, so it is clear but undifferentiated from alternatives.
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 example queries imply when this tool applies (size/mass/scale comparisons in plain words), which is real usage signal. However, there is no explicit statement of when not to use it, no prerequisites, and no routing guidance versus get_page.
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.
get_pagevisualizeScale recipes, convert kitchen units and merge shopping lists. Free.
Read-only pool salt dosing, bag counts, optional costs, and water volume in US gallons and liters.
More than a hundred everyday tools: PDFs, images, text, data, calculators, dice and currency.
Add one secure layer between your agents and this server.
