MCP Station

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

Annotations already declare read-only, idempotent, closed-world, and non-destructive behavior. The description adds useful behavioral context: it enumerates the categories of changes tracked and states the 30-day daily window, which is not captured by the annotations or 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 compact sentences front-load the change categories and follow with the optional names filter. There is no wasted text.

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 the annotations and input schema, the description is mostly complete: it explains what changes are returned and the 30-day window. It could do slightly more to clarify default scope when names is omitted or how results are grouped, but no output schema exists to cover those details.

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 50%. The description adds meaning to the optional names parameter by explaining it as watching specific servers, but it does not clarify the since parameter beyond what is already in the schema. It partially compensates for the coverage gap.

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 resource and scope: registry changes including tool add/remove, schema changes, new destructive tools, server status, and listings over the last 30 days. It is specific and not tautological, but it does not distinguish this from sibling tools like get_server_history.

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?

It implies the tool is for monitoring changes and notes that names can watch specific servers, but gives no explicit when-to-use guidance, no when-not conditions, and no comparison to sibling tools such as get_server_history or search_servers.

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 safety profile: read-only, idempotent, non-destructive and closed-world. The description adds useful behavioral context by naming the response contents, 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?

The description is a single compact sentence with no wasted words. It is front-loaded with the server scope and then lists the returned data, though the fragment style is slightly less immediately scannable than a full 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 one-parameter read tool with strong annotations and no output schema, the description conveys enough about what data comes back to call and interpret it correctly. It does not explain every returned field such as 'rank parts', but the overall shape is adequately covered.

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 is only one parameter and schema description coverage is 100%; the schema already documents 'name' with an example. The description adds no additional parameter semantics 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 clearly scopes the tool to 'one server' and enumerates the kinds of data returned: registry data, measurements, risk, rank parts, URLs and tools. It does not explicitly differentiate itself from siblings such as search_servers, but the singular-server scope is evident.

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?

There is no explicit guidance on when to use this tool versus list/search/history alternatives. An agent can infer it is for retrieving a single known server, but no alternatives or exclusion conditions are stated.

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 this as a safe, idempotent read operation. The description adds useful scope context (up to 30 days, daily results with reachability and response time), but does not mention edge cases like unknown servers or what happens beyond the 30-day window.

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 sentence that front-loads the purpose, data fields, and time bound. There is no wasted text.

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 two-parameter read-only tool with no output schema, the description covers purpose, granularity, returned fields, and a key limit. It lacks explicit return-shape or error-handling detail, but annotations and schema cover most remaining needs.

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 50%: 'name' is documented as Registry name, but 'days' lacks a schema description. The description compensates partially by stating the 'up to 30 days' limit, though it does not explain defaults or units beyond that.

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 ('get server history') and clarifies the payload as daily check results with reachable status and response time. It is clear but does not explicitly differentiate itself from siblings like get_server or get_changes.

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?

There is no explicit guidance on when to use this tool versus alternatives such as get_server or get_changes. Usage is only implied by the mention of daily check results for one server.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds one genuinely useful behavioral fact — that category IDs are stable — implying they can be cached and reused across calls, but says nothing about ordering, size of the result set, or whether the whole taxonomy is always returned.

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?

It is a single short clause with no filler, but it is not front-loaded with a verb-led statement of purpose, so the reader must reconstruct the action. Brevity here shades into under-specification rather than economy.

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 carries the burden of explaining return values, and it partially does by naming the four fields. However it omits the shape of the response (array of objects?), ordering, and whether the list is complete or truncated, which matters for a zero-param enumeration used to look up IDs.

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, so there is nothing for the description to disambiguate; the baseline of 4 applies. The parenthetical '(stable)' on IDs is a useful hint about the value domain even without parameters.

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 text is a noun fragment describing the returned fields rather than a statement of what the tool does, so the agent must infer 'list all categories' from the name and title. It does distinguish the resource (categories) from the siblings, which are all server/tool oriented, but the action verb is absent from the description itself.

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?

There is no guidance on when to call this versus search_servers or get_server, though the zero-parameter schema implies an unqualified enumeration. No prerequisites, no exclusions, no mention of how to use the returned category IDs downstream.

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 cover safety (readOnly, idempotent, closed-world), so the description correctly spends its words elsewhere: result ordering (relevance first, then published rank rules, explicitly no paid placement) and the semantics of similar_to (same categories + same auth, working servers only). Pagination/limit behavior and result shape are not disclosed.

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 resource and source, then usage pattern, then ranking/similar_to behavior. Dense but each sentence carries information; the example could be trimmed slightly but earns its place as a mapping illustration.

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 should say something about what a result contains (name, categories, measurement fields, rank fields), and it does not. With 11 optional parameters, several filters are left entirely to their enum labels. Adequate for correct invocation of the common path, incomplete for interpreting results.

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 73%, so the schema already documents most parameters, and the description's value-add is limited to q/auth/reachable (via the example) and similar_to (semantics beyond 'Registry name of a server to find alternatives for'). Limit, offset, transport, risk, capability and min_success_7d receive no explanation beyond their enum/constraint definitions.

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 and resource ('Find remote MCP servers'), names the data source (Official MCP Registry plus MCP Station measurements), and implies distinct roles for siblings (list_categories for category IDs, get_server for detail). An agent can tell this is the discovery/listing tool without opening any schema.

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?

Tells the agent to convert the user's need into a q string plus filters, and gives a concrete worked example ('crypto market data, no API key, working' -> q=..., auth='none', reachable=true). It also explains the similar_to alternative mode. It stops short of stating when NOT to use this tool versus search_tools or get_server.

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 cover readOnly/idempotent/closed-world, so the safety profile is handled. The description adds that results come from tools/list as the servers report them and include server attribution plus measurements, but leaves vague what 'measurements' means and how the freshness filters (reachable, min_success_7d) behave.

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 sentences, no fat, and the core lookup behavior plus a worked example are front-loaded. Nothing is wasted.

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 ten-parameter faceted search with no output schema, the description should sketch result shape and pagination behavior. It names server attribution and measurements but says nothing about limit/offset semantics or result ordering, leaving 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?

Schema coverage is 70% and the description only illustrates the required 'q' parameter. It adds nothing about the faceted filters (risk, auth, transport, capability, reachable, min_success_7d) beyond what the schema's short descriptions already give.

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 clear verb+resource: find individual tools by name and description, returning the owning server and measurements. The phrase 'individual tools' implicitly separates it from search_servers, but the sibling is never named, so the contrast requires inference.

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 a query example ('pdf table extraction') but no guidance on when to use this versus search_servers, list_categories, or get_server. No exclusions or prerequisites are stated for the ten filter parameters.

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