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

With no annotations, the description carries the full burden, and it never explains what build actually does — whether it mutates state, what it produces, whether it requires preconditions, or whether it is destructive/irreversible. The only behavioral hint is implicit in the word 'buildable' and the read-only resource pointers.

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 short sentences with the resource and action list front-loaded and the alternative-resource guidance second. 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 tool with a mutating action (build), no annotations, and no output schema, the description should explain what build produces and any preconditions or risks. As written, an agent knows the read-only escape hatches but not the semantics of the one action that changes state.

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 67% and the action enum is undocumented in the schema, so the description's enumeration of list/info/build does add meaning. However, it never distinguishes what each action requires or returns (e.g. that name matters only for info/build), and the blueprint_name alias is left to 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 names a concrete resource (buildable image blueprints) and enumerates the exact action verbs (list, info, build), which lets an agent tell it apart from siblings like nido_image or nido_template. The 'manage' framing is a bit broad, but the action list pins down the scope.

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 explicitly advises preferring nido://catalog/blueprints and nido://blueprint/{name} resources for read-only inspection, giving a concrete when-not-to-use signal for list/info. It stops short of saying when build is appropriate versus inspecting a blueprint via the resource first.

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 does substantial work: it discloses that subscriptions are opt-in and session-scoped, that mute retains filters while unsubscribe discards them, and critically that notifications carry only an invalidated URI (no payload). That last point is essential behavioral information for an agent deciding how to consume events. It does not discuss persistence across sessions or delivery guarantees, keeping it from a 5.

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 what the tool controls, then action semantics, then the default state, then where to read health. No sentence is redundant and the ordering follows the agent's decision path.

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 3-parameter session-scoped subscription tool with no output schema and no annotations, the description covers the essentials: default behavior, action distinctions, and notification payload shape. The gaps are the undocumented parameter and any note on subscription lifetime or error behavior, which keeps it below a 5.

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 67%, with the uri and uri_filter parameters already documented and one parameter undocumented. The description adds some semantic context — that subscriptions are per-VM-URI or core resource, and that mute/unmute retain filters — but does not explain the undocumented parameter or clarify the relationship between the two URI parameters. Adequate but reliant on 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 states a specific verb+resource: subscribe/mute/unsubscribe to event streams scoped to this MCP session, with URI or core resource granularity. It is clearly distinct from the sibling resource-management tools (nido_vm, nido_template, etc.). However, the tool name 'nido_events' alone does not convey the subscription-management intent, so the description carries the load well but without naming sibling differentiation 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?

It gives clear operational guidance: default is no notifications, mute/unmute preserves filters while unsubscribe removes them, and status/health lives at nido://system/events. This tells the agent which action to pick and where to look for diagnostics. It lacks explicit 'when not to use' or guidance on choosing between kinds values, but the action-selection semantics are well covered.

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 must carry the full behavioral burden. It lists action names but does not disclose side effects such as whether pull downloads, remove/cache_remove/cache_prune delete data, whether operations are reversible, what permissions are needed, or what the tool returns.

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, front-loaded with the tool's purpose and action set, followed by a concrete resource-preference tip. The action enumeration is somewhat redundant with the schema enum but still useful for quick scanning.

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?

This is a multi-action mutation-capable tool with no annotations and no output schema, yet the description omits action-specific behavior, side effects, prerequisites, return values, and parameter mapping. It gives resource guidance but not enough context to invoke complex actions safely.

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 moderate at 67%, and the schema already describes the image and unused_only parameters. The description repeats the action enum values but adds no action-specific parameter guidance, such as when image is required or that unused_only applies only to cache_prune.

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 plus resource ('Manage the image catalog and cache') and enumerates all supported actions. The image-domain focus clearly distinguishes it from sibling tools such as nido_vm, nido_template, and nido_system.

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?

Explicitly recommends using resources like nido://catalog/images, nido://image/{tag}, and nido://storage/cache for inspection to reduce token usage. It does not explain when each individual action is appropriate or when mutations must be done through the tool versus resources.

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 must disclose behavior. It hints that some actions may not be read-only by recommending read-only resources, but it does not identify which actions mutate system state, require permissions, are destructive, or have irreversible effects such as uninstall or update.

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 short and front-loads the system-wide scope. The action list is somewhat redundant with the schema enum, but it remains concise and does not bury the main purpose.

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 an 11-action system tool with no annotations and no output schema, the description is under-specified. It does not explain action-specific behavior, required parameters per action, side effects, safety constraints, or expected results beyond a bare list of action names.

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 83%, so the schema already documents most parameters, and the baseline of 3 applies. The description only repeats the action names already present in the enum and adds no meaning for key, value, shell, force, or blueprint_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 identifies a system-wide Nido operation dispatcher and distinguishes it from per-VM work, which helps separate it from nido_vm. However, "Access system-wide operations" is a broad category rather than a specific verb+resource, and the long action list only names commands without explaining what they do.

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 only guidance is "Use read-only resources when possible," which is vague and does not name alternatives or specify when to use this tool versus sibling resources. It also gives no warning about when destructive actions such as update, uninstall, or config_set are appropriate.

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, and it discloses almost nothing: delete is a destructive, irreversible operation on reusable infrastructure yet no warning is given, nor any statement about what happens to VMs built from the template or whether the source VM must be in a particular state before create. Only the multi-action dispatch model ('a single tool') is conveyed.

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 short sentences, front-loaded with the resource and the action list, with no filler beyond the slightly redundant 'with a single tool'. Nothing essential is buried.

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?

This is a three-action mutation-capable tool with no annotations and no output schema, so the description should explain per-action preconditions and effects. It instead covers only the action inventory and one alternative, leaving delete semantics and create prerequisites undocumented.

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 75%, near the high-coverage baseline, and the schema already explains name, vm_name and template_name per action. The description adds the valid action values but says nothing about formats, name collisions on create, or whether name is required for delete beyond the enum.

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 ('Manage reusable VM templates') and enumerates the three supported actions, so the agent knows exactly what the tool covers. It does not differentiate against the sibling tools (nido_vm, nido_image, nido_blueprint), which matters since templates sit close to both VM and image concepts.

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?

Provides one concrete routing rule: use nido://fleet/templates when only inspecting names, which steers the agent away from the read path here. It stops short of saying when to prefer create/delete versus blueprint or image tools, so half the action surface has no 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?

No annotations are provided, so the description bears the full behavioral burden, and it discloses almost none. It never says that delete and prune are destructive or irreversible, what prune removes, whether delete frees disk, or whether start/stop are idempotent. The only real disclosure is the inspection-vs-mutation routing hint, which is useful but far short of what a twelve-action mutation surface requires.

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 purpose, then actions, then routing preference, with no filler. The twelve-action enumeration largely restates the schema's action enum, which is mild redundancy, but it does frame the tool's scope before the fallback instruction.

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 god-tool spanning twelve actions and twenty parameters with no annotations and no output schema, the description omits which parameters each action needs, what create returns, and any safety profile for the destructive actions. The resource-preference sentence is good, but it does not compensate for the missing per-action contract.

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 20 parameters and only 55% schema description coverage, roughly nine fields (gui, vcpus, memory_mb, ssh_port, ssh_user, vnc_port, cmdline, accelerators, plus partially name) have no documented meaning anywhere. The description adds no per-action parameter mapping, so an agent cannot tell from it that mapping belongs to port_forward or that user_data only applies to create.

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 ('Operate the VM fleet') and enumerates the twelve supported actions, which lets an agent match its intent to a named operation. It does not explicitly distinguish itself from siblings like nido_template or nido_image, even though the create-related parameters (image, template) overlap with them.

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?

Explicitly routes the agent: prefer the nido://fleet/vms and nido://vm/{name} resources for inspection when the client supports resources, and use this tool for mutations or as a universal fallback. What is missing is any guidance on choosing between actions in ambiguous cases, and no when-not conditions for destructive actions such as delete or prune.

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