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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds a genuine behavioral trait beyond annotations: the prompt-injection warning that returned project text is data, not instructions. It does not explain what happens on a repository digest mismatch, leaving one notable gap.

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 core purpose and followed by a safety caveat. No wasted words.

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 annotations carry the safety profile. But the optional digest parameter is fully undocumented, which is a meaningful omission for a tool whose behavior likely depends on it.

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% and the single parameter (expected_repository_digest) is never mentioned in the description. The name and hash pattern hint at a digest, but the description adds no meaning about when or why to supply it, or how a mismatch is handled.

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 (analyze) and resource (the startup project's static capabilities and relationships), which is more concrete than a tautology. However, it gives no signal distinguishing it from the sibling tools apizr_readiness and apizr_plan_exposure, so an agent must infer the boundary.

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 when-to-use guidance, no prerequisites, and no mention of the sibling alternatives. The only orienting statement is the security caveat, which is behavior, not usage context.

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, so the safety profile is covered. The description adds real value by enumerating the specific actions it will not take (generate, execute, modify configuration, publish), which concretely confirms the plan is advisory only and never applied.

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, purpose front-loaded, and the negative-scope clause placed immediately after so the read-only nature is unmissable. No filler.

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 described, and annotations cover safety. However, for a tool whose core input is a structured policy document, the total absence of guidance on how to build or pass that policy leaves a material gap for an agent.

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% and the description never mentions either parameter. The `policy` object carries a non-trivial nested structure (interfaces, execution.allowed/require, selection, eligibility) and `expected_repository_digest` is a 64-hex pin; neither is explained anywhere, so the description fails to compensate for the coverage gap.

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: "Propose an explicit exposure plan for the startup project." An agent knows this produces a plan rather than applying one, but nothing in the text distinguishes it from siblings apizr_analyze or apizr_readiness.

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 implied rather than stated: the second sentence ("Does not generate, execute, modify configuration or publish anything") signals this is a dry-run/preview step to be used before generating or publishing. No explicit when-to-use condition and no alternatives are named.

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 a safe, idempotent, closed-world read, so the description only needs to add context. It does: the warning that a nonzero exit_code is business evidence rather than a server failure preempts a real misreading of results, which annotations cannot convey. It still omits auth/permission or runtime expectations.

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: purpose first, then the non-obvious exit_code interpretation. Neither sentence is filler and the critical caveat is not 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?

With an output schema present, return-value detail is correctly left out, and the exit_code note usefully frames the output. The single documented-behavior gap is the undocumented parameter, which is minor at this complexity level.

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 one parameter, expected_repository_digest, with 0% schema description coverage, and the description never references it. Nothing explains what digest to supply, why a pinned repository digest matters, or what happens when it is omitted, so the description fails to compensate for the schema gap.

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 (assess) and a specific resource (the startup project's readiness under the startup policy), which is a distinct activity from apizr_analyze and apizr_plan_exposure. It stops short of naming how it differs from those siblings, but the purpose itself is unambiguous.

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 apizr_analyze or apizr_plan_exposure, nor any prerequisites for running a readiness evaluation. The only usage signal is the restated purpose itself, so an agent gets no routing guidance.

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