Mudpie Public MCP

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

Annotations already cover read-only, open-world, idempotent, and non-destructive behavior, so the bar is lower. The description adds genuinely useful behavioral context: answers are grounded in mudpie.ai's published information, include sources, and can be shaped by caller-supplied context.

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 front-load the core action and scope, then add the key behavioral promise (direct answer with sources) and a practical caller instruction. Every sentence earns its place with no repetition of schema or annotation 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?

With no output schema, the description usefully states the return shape ('direct answer... with sources') and handles the optional-context workflow. It is less complete on tool selection, since six sibling tools overlap with parts of this tool's broad scope, and the description gives no routing rule beyond 'ask anything.'

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 schema fully documents all 12 parameters and the description does not need to repeat them. The only added guidance is the general invitation to provide relevant context, which maps loosely to the optional context fields but adds no parameter-specific detail.

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 clearly identifies a general Q&A tool for mudpie.ai covering product, pricing, setup, limitations, and comparisons, promising a direct answer from published information with sources. It doesn't explicitly distinguish itself from siblings like mudpie_pricing or mudpie_compare, so it falls short of a 5.

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 tool's scope is clear ('Ask anything about mudpie.ai...'), which implies when an agent should call it, and 'Add relevant context if you have it; otherwise just ask' gives a small usage hint. However, it never states when to choose a specialized sibling (pricing, compare, requirements_check) or when not to use this tool, so routing is left to inference.

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 establish readOnly, openWorld, and idempotent behavior. The description adds useful non-obvious behavior beyond that: output is grouped per alternative, and missing comparison pages are reported as 'not covered.' This meaningfully enriches the annotations without contradicting them.

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 dense sentences front-load the core purpose, then cover the important missing-page edge case. There is no filler and no repetition of schema content.

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 read-only comparison tool with a fully documented 12-parameter schema, the description covers the output shape (grouped per alternative), the not-covered edge case, and the null convention. It lacks a fuller return-value outline, but the schema and annotations carry most of the remaining burden.

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 parameters are already fully documented. The description's 'use null for unknowns' instruction merely restates what the schema already tells each field, adding no new parameter-level meaning.

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 (Compare) and a specific resource (this website's published comparison pages), and defines a distinctive behavior: grouping results per alternative and flagging alternatives that lack a page. This is clearly differentiated from siblings like mudpie_search, mudpie_pricing, and mudpie_ask_anything, even without naming 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?

Usage context is implied: this tool is for when the user is weighing concrete alternatives against the website's own comparison pages. However, there is no explicit when-not-to-use guidance or named sibling fallback, so an agent has to infer the boundary.

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 mark this as read-only, idempotent, and non-destructive. The description adds useful behavior beyond annotations: it uses published content rather than signed-in data, returns source/freshness/Markdown link, and states that missing or invalid context never blocks the summary. No contradiction with 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?

The description is compact and front-loads the core action, then adds the data-source caveat and required/optional parameter guidance. Every sentence earns its place, and there is no fluff or repeated schema 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 tool with one required parameter and rich schema coverage, the description is complete: it states what the tool reads, where URLs come from, what the output includes, what data is used, and how optional context behaves. No output schema exists, but the description explicitly names the key return components, so an agent has enough to call it correctly.

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 adds one behavioral clarification—'Question and context are optional; missing or invalid context never blocks the summary'—and restates that only url is required, but it does not add meaning for the many other optional parameters beyond what the schema already provides.

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 a specific verb and resource: 'Read a compact extract of one indexed public page returned by mudpie_search.' It clearly distinguishes this tool from mudpie_search by focusing on reading a page-level summary rather than performing a search, and it names the source of the URL.

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 clear usage context: the tool reads pages returned by mudpie_search万余 and states that only url is required. It does not explicitly name alternatives or state when not to use the tool, so it falls short of a perfect score, but the context is strong enough for an agent to choose it appropriately.

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 this as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: it 'abstains when pricing is not published' and 'never invents a quote,' which tells the agent how the tool handles missing information. It also mentions that results include sources. No contradiction with 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?

The description is two sentences and to the point, front-loading the tool's purpose. The second sentence mixes a behavioral promise with a caller instruction ('Include actual task context; use null for unknowns'), which is slightly awkward but not padded. It earns a high score for brevity.

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?

The description states the tool's output (pricing pages with sources) and its fallback behavior (abstain if not published), which is useful given there is no output schema. However, with 12 parameters and several closely related siblings, the description does not clarify output format, what 'sources' means, or how to choose among siblings. It is adequate but leaves room for ambiguity.

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 schema fully documents all 12 parameters. The description only repeats the schema's instruction to 'use null for unknowns' and adds no per-parameter semantics beyond what's already in the property descriptions. 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?

The description identifies this as a pricing-specific tool, stating it returns 'the published pricing pages that apply, with sources' for the user's organisation and outcome. This differentiates it from siblings like mudpie_compare and mudpie_search, which are not pricing-focused. However, it lacks an explicit verb such as 'retrieve' or 'return', and the opening is a noun clause rather than a clear action statement.

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 implies the tool is for pricing questions but never states when to prefer it over siblings such as mudpie_compare or mudpie_search. There is no explicit when-to-use / when-not-to-use guidance, only the behavioral promise to abstain when pricing is unpublished. An agent must infer usage from the tool name and scope.

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 tool read-only, idempotent, open-world, and non-destructive, so the description does not need to repeat that. It adds valuable behavioral detail by disclosing the output semantics: per-requirement statuses with sources. No contradiction with the annotations exists.

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 dense sentences cover input format, output format, and null-handling guidance with no filler. The core instruction is front-loaded and every clause 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?

With no output schema, the description appropriately supplies the return shape: a per-requirement table with statuses and sources. The 13 parameters are fully documented by the schema, and negative constraints like 'use null for unknowns' are present, though explicit sibling routing would make it even more complete.

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, but the description adds format semantics not obvious from the schema alone: requirements can be semicolon-separated in search_query or supplied via the requirements array. This materially helps an agent construct a correct call.

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 clearly states the tool's function: take the user's must-haves and return a per-requirement table with met, not met, or not documented statuses and sources. This is specific to requirement verification, but it does not explicitly differentiate itself from sibling tools like mudpie_compare or mudpie_ask_anything.

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 conveys the trigger context: use this when the user has explicit must-haves to evaluate, and it prescribes how to supply them. It does not state when not to use it or name alternatives, leaving routing to inference.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds that it is 'super fast' and 'semantic', which are minor behavioral traits. It does not disclose return format, pagination, or result limits, but with annotations covering the safety profile, a 3 is appropriate.

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 a single sentence with no waste, and the key guidance ('Include actual task context; use null for unknowns') is front-loaded. It is appropriately sized for a tool whose schema carries most of the parameter documentation.

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 search tool with 13 parameters and no output schema, the description is minimal but the schema covers all parameters. The description does not explain what the return value looks like, how many results are returned, or how the 'detail' parameter affects output, but the schema's detail parameter description partially covers that. Given the tool's complexity (13 params) and no output schema, a bit more context about result behavior would help, but the schema is rich enough to make this adequate.

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 schema already documents all 13 parameters in detail. The description adds the general guidance to 'Include actual task context; use null for unknowns,' which reinforces the null-for-unknowns convention but does not add meaning beyond what the schema already provides. Baseline 3 is correct.

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 ('search') and resource ('mudpie.ai's public pages') and notes it is 'semantic' and 'super fast'. It does not explicitly differentiate from siblings like mudpie_ask_anything or mudpie_page_tldr, but the resource and search nature are clear enough to distinguish it from comparison, pricing, and requirements tools.

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 says to 'Include actual task context; use null for unknowns,' which implies when to use it (when you need to search public pages with context) but does not explicitly state when not to use it or name alternatives. Sibling names like mudpie_ask_anything and mudpie_compare suggest alternatives, but the description itself does not route the agent to them.

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, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful context beyond annotations: the tool is impartial enough to answer 'not us' and the verdict is sourced. It does not go into detail about how sources are returned or what a verdict contains.

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, front-loaded with the key caveat, and no wasted words. It communicates impartiality, purpose, and expected outcome efficiently.

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 12-parameter, open-world tool with no output schema, the description is minimal: it conveys purpose and a sourced verdict but not the shape or behavior of the response, nor explicit call prerequisites. The rich schema and read-only annotations compensate, making this adequate but not complete.

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?

Input schema has 100% description coverage over 12 parameters, so the schema carries most of the semantic weight. The description echoes three core inputs (goal, requirements, alternatives) but adds no format or relationship details beyond the schema. 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?

The description states a clear verb and resource: get a sourced verdict on whether mudpie.ai fits the user's goal, requirements, and alternatives. The phrase 'The answer might be 'not us'' further signals a fit-assessment tool. It does not explicitly contrast with sibling tools, so it misses the top score for 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?

The description implies when to use it: when a user needs an honest fit decision about mudpie.ai, given their goal, requirements, and alternatives. However, it never names alternatives like mudpie_requirements_check or mudpie_compare, nor states when not to use them, leaving routing largely implicit.

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