MCP Marketplace

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

With no annotations, the description carries the transparency burden. It discloses what the tool returns (a structured comparison table plus a short per-field summary) and its efficiency ('without a second pass over each server'). It doesn't mention potential error conditions or rate limits, but for a read-only comparison this is adequate.

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, front-loaded with the core action and fields, followed by usage and return value. Every clause earns its place; no filler.

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 parameter and no output schema, the description fully covers what it does, when to use it, and what the agent receives. It is self-sufficient without needing additional structured metadata.

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% for the single parameter 'slugs', which already describes the min/max items and type. The description adds the domain context that these are MCP servers to compare, but provides no additional syntax or format guidance 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 uses a specific verb ('Compare') and resource ('MCP servers') with explicit scope ('2-5', side by side). It lists the exact fields compared, clearly distinguishing it from siblings like get_server or search_servers.

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 a clear use case: 'Use when a user is choosing between candidates from a search.' It does not explicitly mention when not to use it or name alternative tools, so it stops short of the full 5.

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 no annotations, the description carries the burden, and it discloses case-insensitive matching on display name and the specific return contents (aggregate stats plus per-server list). It doesn't mention error cases or clarify GitHub username case-sensitivity, but overall it provides substantial behavioral 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?

Three sentences, front-loaded with the core purpose, followed by use-case questions and return summary. Every sentence carries meaningful information with no filler.

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 comprehensive for a single-parameter read-only tool: it explains the purpose, use case, matching behavior, and return structure in detail. With no output schema, it names the aggregate stats fields. It could mention empty results, but that's a minor 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?

The schema fully describes the creator parameter (case-insensitive display name or GitHub username, with a hint to use the `creator` field from search_servers). The description only reiterates case-insensitivity and doesn't add new parameter semantics; baseline 3 per schema coverage.

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 ('List') and clearly defines the resource ('all MCP servers by a single creator'), adding aggregate trust signals. This distinguishes it from siblings like search_servers (which likely lists all servers) or get_server (single server).

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 explicitly states the intended use cases ('evaluate a publisher holistically') with example questions, making it clear when to use this tool. However, it doesn't explicitly name alternative tools or state when not to use it, so it stops short of a 5.

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 no annotations provided, the description carries full responsibility for behavioral disclosure. It adds crucial context by revealing that the 'security.critical_findings' array contains high-severity issues and mandating the agent to show them before recommending install. This goes beyond a simple fetch and provides actionable behavioral requirements.

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 and front-loaded with the main action. The first sentence defines the purpose, and the second sentence adds a critical behavioral caveat. Every sentence adds value with no redundancy or fluff.

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?

Despite lacking an output schema and annotations, the description enumerates the returned fields (description, install commands, security findings, ratings, etc.) and the critical safeguard about showing findings. It also specifies where the slug comes from, making the tool's usage context fully understandable.

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 documents the only parameter (slug) with a helpful description (from search_servers or URL). The description only repeats 'by its slug' without adding new semantics, so the baseline of 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 clearly states the tool's action ('Fetch full details for a single MCP server by its slug') and lists the specific resource and scope. It distinguishes itself from siblings like search_servers and compare by focusing on a single server and its comprehensive details.

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 explicit usage guidance: 'Use this as the last step before any install recommendation.' It also implies when not to use it (for searching or comparing servers) but does not explicitly name alternatives or state when-not-to-use conditions, so it falls short of a 5.

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 no annotations, the description is the sole source of behavioral context. It clearly states that this is a listing/read operation and enumerates the output fields, giving a complete picture of what to expect. It does not mention edge cases like pagination, but for a simple list-all tool this is sufficient.

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 and packs both the core purpose and a practical usage hint. No filler or redundancy, making it highly efficient and easy to parse.

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 no-parameter listing tool, the description fully captures what the tool returns and how to use the result. The integration with search_servers adds context that enriches the agent's understanding without needing an output schema.

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 tool takes zero parameters, and the input schema reflects this with an empty properties object. Since there are no parameters to document, the description does not need to add parameter semantics, and the baseline score of 4 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 clearly states the action ('List all MCP Marketplace categories') and specifies the returned fields (slug, name, description, approved server count). This distinguishes it from sibling tools like get_server and search_servers, which operate on individual servers or search results.

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 explicit guidance on how to use the output: 'Use the returned slug as the category filter in search_servers.' This implies a clear use case and integration with a sibling tool, though it doesn't explicitly mention when not to use this tool or alternatives.

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 no annotations, the description carries the burden. It discloses ordering ('Ordered by creation date descending') and return field compatibility ('same security/risk/pricing fields as search_servers'), which helps set expectations. It does not mention rate limits or pagination behavior, but for a simple read-only list tool this is sufficient.

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, front-loaded with the primary purpose, followed by usage guidance and behavioral details. No wasted words—every clause adds useful context.

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 straightforward list tool with fully described params and no output schema, the description covers core behavior: ordering, optional time filters, and the fact that results include security/risk/pricing fields (referencing search_servers). It lacks a full return-shape declaration, but the sibling reference helps fill that 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?

Schema coverage is 100%, so all three parameters (days, limit, free_only) have descriptions in the schema. The tool description adds minimal extra meaning beyond restating the optional date constraint ('Optionally constrain to the last N days'). This meets the baseline but does not exceed it.

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 'List the most recently added MCP servers', giving a specific verb, resource, and scope. It explicitly differentiates from siblings by framing this as a discovery tool for 'what's new', 'latest servers', 'servers from this week', which is distinct from search_servers or get_server.

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 states when to use it: 'Use for discovery: what's new, latest servers, servers from this week.' It also mentions optional date constraint. However, it does not explicitly name alternatives or say when NOT to use it, though the sibling reference to search_servers provides indirect comparison.

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 no annotations provided, the description carries the full burden and delivers thoroughly. It reveals ranking internals (gte-small embeddings + cosine similarity), the meaning of ranking_mode, result fields including security_score and risk_level, and the critical interpretation of critical_findings > 0. This is rich, non-obvious behavioral context that goes far beyond a typical one-line summary.

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: four sentences that progress logically from what the tool does, to how results are ranked, to what results contain, to the recommended follow-up with get_server. Every sentence adds necessary information with no fluff or repetition of schema details.

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?

Despite having 7 parameters and no output schema, the description supplies enough context for an agent to use the tool effectively: semantic search behavior, response field expectations, and safety-critical guidance around critical_findings. The only missing pieces (pagination defaults, error behavior) are adequately covered by the schema or are not essential for a search tool.

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 covers all 7 parameters with individual descriptions, so the baseline is 3. The description adds above-baseline value by explaining how query interacts with semantic ranking, how sort defaults change based on query presence, and why the transport filter excludes SSE (a known catalog limitation). These insights are not present in the schema alone.

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 ('Search the MCP Marketplace catalog') and immediately clarifies the search mechanism (semantic similarity + keyword). This clearly distinguishes search_servers from siblings like get_server, list_categories, and recently_added, all of which serve different purposes.

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 strong context for when to use this tool: for free-text and natural-language discovery across the catalog. It also explicitly instructs to call get_server before recommending an install, which is a clear follow-up guideline. However, it does not explicitly mention when to prefer siblings like similar_to or compare, so it falls short of a 5.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It does well by explaining the embedding mechanism, sorting by cosine similarity (highest first), exclusion of the reference server, and the inclusion of security/risk/pricing fields in results. This gives the agent a solid understanding of expected behavior, though it omits edge cases like empty results or error handling.

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 well-structured and front-loaded with the core purpose in the first sentence. Subsequent sentences provide usage context, technical method, sorting order, and output field details—each sentence earns its place. It is appropriately sized for the tool's complexity, with no wasted words or repetition.

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?

Given no output schema and no annotations, the description is reasonably complete. It explains what the tool returns (servers sorted by similarity), how results are computed (embeddings, cosine similarity), and key output fields for comparison. It could additionally specify the exact response format (e.g., list of server objects), but the description covers the most critical aspects thoroughly.

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 does not add extra meaning beyond the schema for each parameter; the schema already explains slug, limit, and free_only. However, the overall description provides context for how these parameters affect behavior (e.g., excluding the reference, limiting results), but this is not per-parameter added value.

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: "Find MCP servers that are semantically similar to a reference server." It uses a specific verb and resource, and distinguishes from sibling tools by focusing on semantic similarity rather than search or comparison. Examples like 'like this but safer' further clarify the intended use case.

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 explicitly says when to use: "Use when a user picked a candidate but wants alternatives." This provides clear context for invocation. It does not explicitly name alternative tools or state when not to use, but the 'Use when' instruction is strong enough to guide selection. The mention of search_servers in the output context also hints at a related tool.

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