mcpcost

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

With no annotations, the description carries the full burden and does so well: it discloses the exact protocol steps performed (initialize, tools/list), the absence of credential requirements, a concrete timeout, and the returned fields including the token-cost measurement with its exact-vs-estimate fallback behavior.

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?

Front-loaded with the action and tightly packed, but the single long sentence stacks multiple parentheticals, which slightly taxes readability. Every clause still earns its place, so only a minor deduction.

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 must explain return values, and it does: status, protocol, tools, and token cost with exact/estimate qualification. For a one-parameter probe tool this is 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% and the single parameter is already documented as an HTTPS URL of the MCP endpoint. The description adds only marginal semantics ('no credentials'), so the baseline 3 for a fully covered single-param schema 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?

States a specific verb and resource: it connects to an MCP server URL live, performs initialize and tools/list, and reports status, protocol, tools, and token cost. It explicitly distinguishes itself from lookup_server for registry servers, so an agent can route correctly without opening the 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?

Names the alternative (lookup_server) and the condition that selects it ('For registry servers prefer lookup_server'), which is the primary routing decision for this tool. It also discloses operational constraints (no credentials, 10 s timeout) that govern when the live probe is viable.

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?

No annotations exist, so the description carries the full burden. It helpfully discloses the return payload (status, protocol, tool count, token cost, latency) and implies cached 'latest probe' data rather than a live fetch, but never states that it is read-only, side-effect free, or subject to rate/freshness limits.

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, front-loaded with the resource and the payload list; every clause conveys either scope or return content. No filler, though the field enumeration is dense enough to read as a list rather than prose.

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 annotations and no output schema, the description does the work of describing the returned fields, which is good. It still omits the check_server relationship and any statement about data freshness or safety profile, leaving meaningful gaps for a lookup tool with a confusingly similar sibling.

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 there is only one parameter, so the baseline is 3. The description goes slightly beyond the schema by giving the concrete accepted format (io.github.owner/name) alongside the URL form, which helps an agent construct a valid 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?

Names a specific verb (look up) and resource (one registry server) and enumerates the returned fields — status, protocol, tool count, token cost, latency. The 'one server' scope implicitly separates it from search_servers and registry_summary, but the near-identical sibling check_server is never distinguished.

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?

Single-server scope implies when this is preferred over search_servers/registry_summary, but there is no explicit when-to-use guidance and, critically, no differentiation from check_server, which an agent would plausibly confuse with this tool. Usage is inferable but not 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?

With no annotations, the description carries the full behavioral burden. It usefully discloses data freshness ('latest daily run') and the shape of the aggregate, but says nothing about whether results are cached, how often the daily run refreshes, or any access constraints. No params means low risk, so this partial disclosure is defensible but not rich.

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 that packs the aggregate's contents into a compact list with no filler. It is slightly list-like and omits an explicit verb, but 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 zero-parameter, annotation-free read tool with no output schema, enumerating the returned aggregates (counts, percentiles, protocol versions, heaviest servers) effectively substitutes for a schema. The remaining gap is refresh/caching semantics, which is minor.

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. No misleading parameter hints are present.

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 the resource concretely and enumerates what the aggregate contains (server counts, token cost percentiles, protocol versions, heaviest servers), so an agent knows this is a report-style read, not a per-server lookup. It is clearly distinct in substance from check_server/lookup_server/search_servers, though it never says so explicitly.

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 is only implied: the aggregate framing suggests 'use this for an overview, use the siblings for individual servers,' but no when/when-not condition or alternative is stated. An agent can infer the split from the sibling names, but the description does not do the routing work.

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 to lean on, the description carries real behavioral weight: it discloses the default sort order (exact Claude token cost), the 20-per-page cap, and the page-to-cursor handoff at page 20. It stops short of describing result contents or rate/limit behavior.

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, no filler. The search scope and default sort are front-loaded, with pagination as the follow-on practical detail.

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 parameter-light search tool with no output schema, the description covers the essentials an agent needs to call and paginate correctly. It could still say more about what a returned server record contains, but nothing critical to invocation 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 coverage is only 60%, and the description compensates by clarifying the default sort value and the page/cursor interaction (pages valid to 20, then use the `next` cursor) — meaning not derivable from the raw schema. It does not explain the `status` enum or the sort enum variants, leaving some gaps.

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 concrete verb+resource ("Find servers") and even names the matchable fields (name, title, description, host), so the agent knows exactly what corpus is searched. It does not explicitly distinguish itself from siblings like lookup_server or check_server, which is the only thing keeping it from 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 description never says when to reach for this tool versus lookup_server, check_server, or registry_summary. It hints that filters are optional and describes pagination mechanics, but provides no routing guidance or exclusion conditions.

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