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

While annotations already indicate a mutating operation (readOnlyHint: false), the description adds substantial behavioral context: the dry-run safety mechanism, the removal of every line item, and the post-removal verification that the cart is empty. This goes beyond the structured annotation data.

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 with no redundant words. It front-loads the primary action and then efficiently explains the two modes of operation.

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 simple one-parameter tool with no output schema, the description covers all essential aspects: purpose, required authentication context (signed-in), the destructive vs. safe modes, and the verification step. It is sufficiently complete for an agent to invoke appropriately.

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 schema already describes confirm as 'Must be true to proceed... returns a preview', but the description extends this by explaining what the dry run lists and that confirm triggers a re-read to verify emptiness. This adds meaningful behavioral detail beyond the schema's basic preview note.

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 with a specific verb ('Remove'), a resource ('Groupon cart'), and scope ('ALL items'). It is immediately distinguishable from sibling tools like view_cart (which reads) and purchase (which transacts).

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 provides clear context on how to use the tool safely, explaining the dry-run behavior without confirm:true and the actual removal with confirm:true. It does not explicitly name alternatives, but the usage scenario is obvious and the confirm parameter is thoroughly explained.

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 destructiveHint=false. The description adds meaningful behavior beyond that: it defaults to a slim projection, accepts either a slug or full URL, and documents that view='full' returns Groupon's whole record. It does not detail error cases, but for a simple read-only fetch this is sufficient and it does not contradict the 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 with no filler. It front-loads the action and resource, then states the default return shape and the way to get the full record, earning its place in every clause.

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 single-item fetch with annotations covering safety and the schema covering both parameters, the description is nearly complete. It lists the slim projection fields and the full-record switch, though it does not discuss invalid IDs or when to prefer search_deals, which are minor gaps.

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 input schema already fully documents dealId as 'Deal permalink slug, or full deal URL' and describes the view enum and its effects in detail. The description reinforces the slug/URL behavior and the default slim vs. full distinction, but adds little semantic meaning beyond what the schema provides, so the baseline of 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 uses a specific verb ('Fetch a single Groupon deal') and resource identifier ('permalink slug or full deal URL'), and lists the fields returned in the slim projection. This clearly distinguishes it from sibling tools like search_deals or list_categories.

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 makes the intended use clear: use this when you already have a known deal permalink slug or full URL and want the complete or slim deal record. It doesn't explicitly exclude search_deals for query-based discovery, but the emphasis on 'a single deal' and the URL-based key provides unambiguous context.

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, so the read-only nature is disclosed. The description adds the version detail, but no other behavioral traits (e.g., response format, error conditions) are described. With annotations covering the safety profile, this is adequate but not extensive.

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 extremely concise, consisting of two short sentences that front-load the core purpose. The second sentence adds valuable roadmap context without any wasted words.

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 simple health check tool with no parameters and no output schema, the description is complete. It states what it does, what it reports (running state and version), and provides context about the tool's phase, making it fully sufficient for an agent.

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 input schema is empty with zero parameters, so the schema fully covers parameter semantics. The description does not need to add parameter details; baseline for zero parameters is 4, and no additional info is necessary.

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 reports that the groupon-mcp server is running and its version. The verb 'Report' and specific resource 'groupon-mcp server' make the purpose unambiguous, and it is clearly distinct from the sibling deal-related 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 second sentence 'Deal-read tools arrive in a later phase' provides context that this health check is the primary use for now, implicitly guiding the agent to use this tool for server status checks rather than expecting deal functionality. It lacks an explicit exclusion or alternative, but the implication is clear.

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?

The readOnlyHint annotation already signals this is a safe read operation. The description adds useful behavioral context by disclosing the default slim tree shape and the option to request Groupon's full payload, which goes beyond the annotation alone.

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. The core action is front-loaded, and the optional behavior is stated compactly in the second sentence.

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 simple read-only tool with one optional enum parameter and no output schema, the description fully covers what the tool does, the default response shape, and how to get the fuller response. Nothing essential 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?

Schema description coverage is 100% and the single view parameter is already well documented with enum values and behavior. The description adds little beyond reinforcing the default compact behavior, so the schema carries the semantic weight.

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 uses a specific verb and resource: 'Fetch Groupon's category taxonomy tree.' It clearly distinguishes itself from siblings like search_deals and purchase, since it is the only tool dealing with category taxonomy.

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 makes the intended use obvious by stating exactly what it returns and how to control the response shape with view='full'. It does not explicitly name sibling alternatives or state when not to use it, but the use case is clear enough that no exclusion is strictly necessary.

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?

The description discloses key behaviors beyond the readOnlyHint: it previews changes without confirm, re-reads the cart after adding, returns a checkout URL, and cannot complete the order. These are not implied by the annotations and significantly inform the agent.

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 three sentences long, front-loaded with the main purpose, and presents the dry-run/confirm logic and limitation clearly without redundant phrases.

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 tool has moderate complexity with a dry-run mode and required confirmation, but the description covers the behavior, the return value (checkout URL), and the payment constraint. It also directs users to groupon_get_deal for optionId, making it sufficiently complete given the schema richness.

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 explains all five parameters. The description adds context about the dry-run/confirm flow, but doesn't add per-parameter details beyond the 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 opens with 'Add a Groupon deal option to your cart', clearly identifying the action and resource. It distinguishes itself from sibling tools like search and view_cart, and explicitly states it cannot place the order.

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 explains the dry-run vs confirmed execution modes ('WITHOUT confirm:true this is a DRY RUN... WITH confirm:true it adds the item...'), and clarifies that payment is completed externally. It also notes the limitation ('It CANNOT place the order') and points to native checkout as an alternative.

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?

With readOnlyHint=true already declaring this is a safe read operation, the description adds useful behavioral context: results are slim by default, view='full' changes the response shape, and omitting query switches to browse mode. This goes beyond the annotation without contradicting it.

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 front-loaded sentences convey the core behavior, the query/browse distinction, and the output-shape switch with zero filler. 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?

The description is complete enough for a read-only search tool with richly documented schemas and defaults. It covers the main usage decision (query vs. browse) and the output-shape decision (compact vs. full), though pagination and limits are left to the schema rather than surfaced in the description.

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 parameters thoroughly. The description paraphrases the query/view guidance but does not add meaning beyond what the schema provides, so the baseline of 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 names a specific verb ('Search or browse'), a clear resource ('Groupon deals'), and a scope ('for a city (division)'). It also distinguishes the two main modes of this tool (free-text search vs. category/city browse), which separates it from siblings like groupon_get_deal and groupon_list_categories.

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 conditional guidance: pass `query` for free-text search, omit it for browsing, and use view='full' when full records are needed. It does not explicitly name sibling tools or state when not to use them, so it stops short of a 5, but the internal usage context is unambiguous.

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 the description adds valuable behavioral context by specifying the session requirements: 'GROUPON_SESSION_COOKIE, or the fetchproxy browser bridge signed into groupon.com.' This goes beyond the annotation's safety read-only indication.

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 long, front-loaded with the core action, and every word adds value. It is concise without omitting important prerequisite 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 simple view operation with no parameters and no output schema, the description adequately covers what it does and prerequisites. It could mention response format (e.g., list of items), but the tool's simplicity makes it less critical.

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?

There are zero parameters, so the schema is trivially covered. The description correctly avoids inventing parameter details, and there is no need for additional parameter semantics.

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 and resource: 'View the items currently in your signed-in Groupon cart.' This clearly distinguishes it from sibling tools like groupon_clear_cart and groupon_purchase, which have different actions.

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 clearly indicates a prerequisite: 'Requires a Groupon session (GROUPON_SESSION_COOKIE, or the fetchproxy browser bridge signed into groupon.com).' It provides context for when this tool is usable, though it does not explicitly mention alternatives or when not to use it.

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