install_agent_marketplace_action

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

With zero annotations, the description carries the full burden and does substantial work: it discloses that installation pins exactly one revision, that it never grants execution approval (a critical safety property), and that omitting deployment_targets leaves the installation invokable but outside the automatic tool catalog. This is notably rich disclosure for a mutating tool. It does not cover idempotency semantics or reversibility, but the core behavioral traits an agent needs to avoid misuse are present.

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 sentences, zero filler. The purpose is front-loaded in sentence one, followed by an input constraint, then behavioral consequences, then the optional parameter semantics. Every sentence adds non-redundant information and the ordering leads with the most 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?

The output schema covers return values, and the description covers the critical input-validity and safety behaviors well. But the required idempotency_key parameter is completely unexplained (purpose, format, generation guidance), and the description never notes that installations are reversible via uninstall_agent_marketplace_action. For a 4-parameter mutation tool with no annotations and 0% schema coverage, these are material omissions.

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, and it does meaningfully for deployment_targets: format (JSON array), governed value examples, and the behavioral consequence of omitting it. However, listing_id, revision_id, and especially idempotency_key receive no semantic explanation — their meaning is only inferred from 'pins one revision' and the schema titles. For a required parameter like idempotency_key, that is a real 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?

The first sentence uses a specific verb+resource pair ('Install persisted UUIDs') and names the exact source of valid inputs (list_agent_marketplace_listings), which cleanly separates it from the activate/pin/uninstall siblings in the same marketplace family. The second sentence further disambiguates by explicitly rejecting IDs from search_agent_marketplace. An agent can tell exactly what this tool does without opening any sibling 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?

The description gives explicit guidance on which upstream listing source is valid and which is not ('Synthetic IDs returned by search_agent_marketplace are not accepted'), which is a concrete when-to-use/when-not-to-use constraint. The statement that installation 'never grants execution approval' implicitly routes agents who need approval-granting behavior toward a different sibling, though it never names activate_agent_marketplace_action or pin_agent_marketplace_action as explicit alternatives.

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