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

With no annotations, the description carries the full disclosure burden and does it well: it states read-only semantics, gVisor sandbox isolation, the exact credential scope (get/list/watch on one namespace), and that no approval gate exists. It stops short of pagination or error behavior, but the safety and permission profile is unusually well covered for an annotation-free 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?

Three short sentences, front-loaded with the safety-critical 'Read-only.' qualifier followed by scope, environment, and approval status. Every sentence adds information; no filler or repetition.

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-format explanation is unnecessary, and the description covers read-only status, execution environment, credential scope, and approval behavior for a single-parameter tool. The one remaining gap is that the namespace default and format are never mentioned in either the description or the schema.

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 lone parameter. It only gestures at 'the target namespace' without naming the parameter, giving the default value ('demo-app'), or indicating accepted namespace formats. The agent must open the schema to learn anything actionable about the input.

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 ('Lists pods and their phase') plus an explicit scope ('in the target namespace'), so the agent knows exactly what is returned. It does not differentiate from siblings, but the siblings (terraform_plan/terraform_apply) are an unrelated domain, so no routing confusion exists. Minor tension: the name says 'pod status' (singular) while the description lists pods (plural).

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?

'Read-only' and 'Runs immediately; no approval needed' imply when this is safe to call, and the namespace scoping implies the context. There is no explicit when-to-use/when-not statement or named alternative, so usage is only implied rather than 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 and does so well: it flags HIGH RISK mutation, explains that the no-approval path is non-destructive (computes plan, records pending approval), and discloses approval lifecycle traits (single-use, expiring, parameter-bound). This is far beyond what a bare 'apply' would convey.

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 tight sentences with the risk warning and the two-phase contract front-loaded; no filler. Dense but readable, and every clause adds operational 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?

Output schema exists so return-value documentation is unnecessary, and the description still names the key return (approval id). Combined with the risk warning and approval lifecycle, an agent has everything needed to call this correctly and 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 0%, so the description must compensate; it fully explains approval_id semantics (optional, single-use, expiring, must match exact parameters, absence means no apply). working_dir is never explained, which is the one remaining gap, but the high-risk parameter is covered.

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 ('mutates real infrastructure', Terraform apply) and immediately clarifies its two-phase nature, which separates it from terraform_plan's pure-preview role. An agent can tell what this does and when it would fire 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?

Explicit conditional workflow: call without approval_id to compute a plan and register a pending approval, then call again with the returned approval_id to execute. It also states the human review happens out-of-band, so the agent knows not to wait on this call for the mutation to occur.

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 and does well: it discloses immediate sandbox execution (no confirmation gate), that the plan is persisted as durable state, and that output is annotated on destructive changes like forced replacement. It omits auth/permission requirements and failure behavior, which keeps 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 tight sentences with no filler, front-loaded with what the tool does before the sandbox/persistence and destructive-change details.

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, and the description covers execution model, persistence, and destructive-change signaling. The main residual gap is parameter semantics for working_dir, which neither schema nor description pins down.

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% for the single working_dir parameter, so the schema adds nothing. The description hints that the module lives 'under the terraform/ root', which weakly constrains the path, but it never states whether working_dir is absolute, relative, or relative to that root.

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 ('Computes a Terraform diff for a module'), and scopes it to the terraform/ root. It also implicitly distinguishes itself from the sibling terraform_apply by framing itself as the review step that a 'subsequent apply' consumes.

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 clear context for use: it runs immediately and produces a persisted plan that a later apply executes, which tells the agent this belongs before terraform_apply. It stops short of explicit when-not-to-use guidance or naming the alternative tool directly.

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