TestedMCP

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

Annotations already cover the safe read-only, idempotent, non-destructive profile. The description adds useful behavioral context by saying the tool should only return a replacement when evidence exists and otherwise returns 'none identified', which helps prevent hallucinated replacements. It stops short of describing evidence sources or lookup behavior in more detail.

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 definition is a single efficient sentence with no filler. The core purpose is front-loaded, and the evidence condition and fallback are included compactly.

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 and strong annotations, the description provides enough context to call it correctly: it identifies the replacement lookup and the fallback behavior. It could be more complete by clarifying the relationship to is_deprecated or what counts as evidence, but the essentials are present.

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 parameter is already documented as a TestedMCP slug or npm package name. The description does not add any parameter-specific meaning, but that is acceptable given the rich schema coverage. Baseline 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 states a specific resource: a maintained replacement for a deprecated MCP server. It also adds an evidence condition and fallback, so it is more than a restatement of the name. It does not explicitly differentiate itself from siblings such as is_deprecated or search_servers, which keeps it at a 4.

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 phrase 'only when there is evidence (e.g. npm's message)' implies when the tool is appropriate, but it is framed as a behavior condition rather than an explicit when-to-use rule. It does not name alternatives or state clearly that the tool should be used after is_deprecated confirms deprecation. Usage is implied rather than fully specified.

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 annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add context. It does so usefully by disclosing the return contents — score, per-test results, evidence, test date — which is the main behavioral fact an agent needs and is not available anywhere else since 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?

One sentence, front-loaded with the primary value (the score) followed by the supporting detail. No filler and nothing that could be cut without losing 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 one-parameter read tool with no output schema, the description carries the return-value burden well by enumerating what comes back. It is slightly incomplete on edge cases — no-score-yet servers, or not-found handling — but nothing an agent needs to make the call correctly 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?

There is only one parameter and schema description coverage is 100%, with the schema itself giving the slug/npm-package format example. The description adds no additional meaning about the parameter, so the baseline 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 the resource (one MCP server) and spells out exactly what is returned: a 0-100 score, per-test results and evidence, and the test date. The verb is implicit in the name 'get_score' rather than stated, but the payload is unambiguous and clearly distinct from siblings like search_servers or is_deprecated.

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 single required slug_or_package parameter signals that this is a lookup for a specific, already-identified server. There is no explicit statement of when to call this versus search_servers (to find a server) or is_deprecated, and no mention of what happens when a server has no score yet.

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 detail — that the deprecation message is null when there is none — but says nothing about lookup failures (unknown slug/package) or the shape of the response, and there is no output schema to fall back on.

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 tight sentence with no filler, and the most important element (deprecation status) is front-loaded. It is a fragment rather than a complete sentence, which slightly hurts readability but costs nothing in length.

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 one-parameter read lookup this is close to sufficient, and the annotations carry the safety profile. However, with no output schema the description is the only source of return-value information, and it only names the fields without indicating whether status is boolean/string or how the verification date is formatted.

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?

With 100% schema description coverage and a single required parameter whose description already explains 'slug or npm package name' with an example, the schema does the work. The tool description adds no extra meaning about accepted forms or precedence when the string is ambiguous between a slug and a package name.

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 specific resource (deprecation status, npm deprecation message, verification date), so an agent can tell this is a deprecation-lookup tool. It is a noun-phrase fragment with no verb and never distinguishes itself from siblings like get_replacement, so it stops 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?

There is no guidance on when to call this versus get_replacement (the obvious follow-up for a deprecated server) or get_score. Nothing states prerequisites, e.g. that a slug or npm package name must already be known.

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, idempotentHint=true, destructiveHint=false, and the description adds a useful behavioral detail (results sorted by score). However, it omits that deprecated servers are excluded by default (the include_deprecated default is false) and says nothing about result count limits or truncation, which matter for an agent consuming results.

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 with zero filler, and the core purpose plus result ordering are front-loaded. Nothing is redundant with the title or name.

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?

Evidence from the description is thin on the two optional parameters and the default exclusion of deprecated servers, but for a read-only search tool with no output schema it covers the essential purpose. Given the low schema coverage, a bit more on limit/include_deprecated would close the 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 description coverage is 0%, so the description must carry parameter meaning, and it only partly does: "by name, package or category" maps loosely to query and category. The limit (default 10, max 50) and include_deprecated (default false) parameters are left completely unexplained in both schema and description.

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 ("Search MCP servers tested by TestedMCP") and names the matchable fields (name, package, category), plus the result ordering by score. It does not explicitly differentiate itself from siblings like get_score or is_deprecated, but those serve clearly distinct lookup purposes, so an agent can still route correctly.

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 phrasing suggests finding servers by name/package/category, but there is no explicit when-to-use statement, no exclusions, and no mention of when to reach for get_score or is_deprecated instead. The scenario is inferable but not spelled out.

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