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

With no annotations, the description carries the full burden, and it does disclose two valuable traits: the server becomes live immediately and its tools are exposed as '<alias>__<tool>'. It says nothing about whether the install persists across restarts, what happens on a bad identifier or unreachable command, whether it is idempotent when adding the same server twice, or what permissions/network access are required for a mutation of this kind.

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 short sentences, front-loaded with the action, then the parameter semantics, then the observable effect. No filler, and the parenthetical cross-reference to capability_search is placed exactly where the agent would need it.

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?

An output schema exists, so return values needn't be explained, and the core semantics are covered for a two-parameter tool. But this is an unannotated state-mutating operation: persistence, failure behavior, and the interaction with capability_remove/capability_list (does the new server show up there?) are all unaddressed.

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 0%, so the description must compensate, and it handles the required `identifier` thoroughly — both accepted forms with literal examples. The `alias` parameter is only conveyed indirectly via the '<alias>__<tool>' naming template; the description never says what happens when alias is omitted/null or whether it must be unique.

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?

"Install and mount an MCP server" is a specific verb+resource pair, and the description immediately distinguishes the two identifier modes (registry name vs local stdio command). It also explicitly points at capability_search for the registry-name case, so the agent can separate this from its siblings without opening schemas.

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 names the condition for one path ("see capability_search" when you need a registry name) and shows a concrete local-command form, which is clear usage context. It stops short of stating when to use capability_add versus capability_consider or capability_verify, or any prerequisite/ordering (e.g. search first, consider before add).

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 does well: it discloses the 10-minute cache window and the degradation path during registry outages (falls back to 'implement it yourself' advice). It stops short of saying whether the call has any side effects or what latency/cost to expect, which is the main remaining gap for a zero-annotation tool.

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?

Four short sentences, front-loaded with the core purpose, then usage timing, then operational caveats, then the sibling pointer. No sentence is padding and each adds a distinct decision-relevant fact.

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?

An output schema exists, so return-value explanation isn't required, and the description still flags that results include local verification status plus the caching/failure behavior. The only real omission is the `limit` parameter, which matters for a tool that surfaces ranked suggestions.

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 0%, so the description must compensate. "Given a subtask description" usefully frames the `task` parameter as a subtask rather than a whole task, but the `limit` parameter (default 5) is never mentioned in the description, leaving half the parameters undocumented anywhere.

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: suggest existing capabilities from the official MCP Registry for a given subtask, with local verification status. It also explicitly distinguishes itself from the sibling capability_search (raw candidate lists), so an agent can choose between them without opening a 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?

"Call while decomposing a task, before implementing anything yourself" gives a concrete lifecycle point, and "Use capability_search for raw candidate lists" names the alternative and the condition that selects it. Both the when and the when-not 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?

No annotations are provided, so the description carries the full burden. It does disclose what each entry contains (tools, source, health, verification status), which is genuinely useful, but it never states that the operation is side-effect free, whether it requires the servers to be reachable, or how costly/slow the health probing is.

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 with zero filler; the verb and scope come first and the returned fields follow. Nothing is repeated from structured data.

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?

An output schema exists and the parameter list is empty, so the remaining burden is small and the description covers the core behavior plus the shape of each listed entry. It stops short of stating read-only semantics or any operational caveats around the health check.

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?

Zero parameters, so there is no parameter semantics to explain; the baseline for a no-arg tool is 4. The description correctly avoids inventing filter options that the empty schema does not support.

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 (List) and resource (mounted capability servers), plus the fields surfaced (tools, source, health, verification status). The enumeration framing implicitly contrasts with capability_search, but no sibling is named 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: 'List mounted' suggests a full inventory sweep, in contrast to a query-style tool like capability_search. There is no explicit when-to-use, when-not-to-use, or alternative-routing guidance.

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 behavioral burden and does well by disclosing the concrete side effects: subprocess termination, tool unregistration, and persisted config removal. It omits whether removal is irreversible or requires specific permissions, but the core mutation behavior is transparent.

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, front-loaded sentence with no filler; every clause adds specific operational 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?

An output schema exists, so return values need not be explained. The description adequately covers the removal side effects and scope; only a stronger irreversibility or authorization warning would make it fully 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 description coverage is 0%, so the description must compensate for the single alias parameter. It partially does by showing that alias is used in the '<alias>__<tool>' tool naming convention, but it does not define alias format, source, or validation constraints.

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 ("Unmount") and resource ("capability server") and enumerates the exact effects: terminate subprocess, unregister tools, remove persisted config. It is clearly distinguishable from sibling tools like capability_add, capability_list, and capability_search.

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 strongly implied by the removal semantics, but the description does not explicitly state when to use this tool versus alternatives (e.g., capability_add for adding, capability_verify for checking). No when-not conditions or sibling routing are provided.

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 burden. It discloses the source (official MCP Registry), the return fields (name, description, version, packages with npm/pypi identifiers), and the downstream handoff, which is genuinely useful. It omits that this is a read-only lookup, whether queries are fuzzy or exact, and any rate limit or empty-result 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?

Three sentences with no filler, front-loaded with the action and source before the return shape and handoff. Every sentence adds a distinct piece of 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?

An output schema exists, so return values are partly covered for free, and the description additionally names the key fields and the install handoff. The remaining gap is the undocumented limit parameter and unspecified behavior for zero results, which is minor for a two-parameter 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?

Schema coverage is 0%, so the description has to compensate. It implies query is a string used to match servers and hints the returned name is what feeds capability_add, but the limit parameter (default 5) is never mentioned in either the schema or the description, leaving one of two parameters undocumented.

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 gives a specific verb and resource ('Search the official MCP Registry for installable MCP servers') plus the shape of the result, which no sibling provides. It is clearly distinct from capability_add/consider/verify/list/remove, and it even routes the agent forward to capability_add.

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 states the context of use (finding installable servers in the official registry) and names the next step explicitly: 'Pass a server's name to capability_add to install it.' It does not say when to prefer this over siblings like capability_consider or capability_list, so an exclusion clause is missing.

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 and does a good job: it discloses that the tool performs outbound calls (ping, list_tools, probe) and, importantly, that results are written to the local trust store — a side effect an agent would otherwise not anticipate. It omits failure/timeout semantics and whether the trust-store write is reversible, keeping it out of 5 territory.

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 short sentences, no redundancy: the mechanism comes first, the side effect second, and the scope limitation last. Every clause adds information the agent needs.

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?

An output schema exists, so return values need not be described, and the description adequately covers mechanism and side effects for a zero-annotation tool. The one meaningful gap is the unexplained 'alias' parameter, which leaves the invocation less complete than it could be.

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 0% and the single required parameter 'alias' is never mentioned in the description. The phrase 'a mounted server' only weakly implies that alias identifies which mounted server is being probed; the agent must infer format, source, and validity from the schema title 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 gives a specific verb (smoke-test) and a specific resource (a mounted server), then enumerates the exact steps: ping, list_tools, and a single safe zero-argument probe. It is clearly distinct from the sibling set (search/consider/add/list/remove), which concern discovery and lifecycle rather than liveness checking.

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 states the use case (establishing liveness of a mounted server) and explicitly bounds it with 'This is a liveness check, not a security audit', telling the agent when not to expect security findings from it. It does not name a sibling alternative or a prerequisite condition, so it falls just 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.