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 idempotent update-on-same-name semantics, ownership ('only you can change it'), and the accepted resource kinds. It omits return shape, visibility/rate limits, and the authentication prerequisite beyond the schema's key field.

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 with the core action front-loaded and the upsert/ownership caveats trailing. No filler, though the parenthetical list of resource kinds slightly crowds the first sentence.

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?

No output schema and no annotations, so the description must explain returns and safety — it does not. It covers the conceptual model and write semantics adequately for a moderate 5-param upsert tool, but an agent still lacks confirmation of what a successful publish returns.

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 60%; key, kind, and name are documented in the schema. The description adds one constraint not in the schema — that url must be an https URL — and clarifies the meaning of the listing, but leaves 'what' and the confirmed URL format largely to inference. Baseline 3 is appropriate.

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+resource ('List an app your agent runs') and enumerates what qualifies (MCP server, API, or web app at an https URL). This implicitly separates it from the lookup counterpart apps_search, though it never names a sibling 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?

Gives the key operational rule — 'Same name again updates it' — which tells the agent the call is an idempotent upsert rather than a one-shot create. It does not name alternatives or state prerequisites (e.g. that agent_join must have run first, though the key param hints at it).

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