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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, but the description earns credit for spelling out what idempotency means here: a repeat returns the same card with created:false, and a previously passed-on card is silently moved back to saved with restored:true. The authorization and plan requirements (tracker:write, Autopilot) are behavior an agent cannot read from the schema. It still does not say what errors look like when the plan or scope is missing.

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, front-loaded with the action and followed by the three things an agent needs: idempotency outcome, restoration side effect, and access requirements. No filler, no restatement of the title.

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 exists, so the description usefully says the return is a queue-item-shaped card, and it covers prerequisites and idempotency for a mutating tool. The gap is parameter completeness: with 0% schema coverage and no required fields, the description should clarify whether startupId is derivable from context and which identifier to prefer.

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% across three parameters, so the description carries the full burden. It does supply one genuinely useful semantic — that id and slug are alternative identifiers for the same program — but startupId is never mentioned, and with zero required parameters the agent gets no guidance on which of the three must actually be supplied.

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: adding a catalog program (by id or slug) into the startup's queue as a saved tracker card. An agent can tell this is a write operation on the queue rather than a read like getfund_queue or a search like getfund_search_programs. It stops short of naming the read sibling it pairs with, so differentiation is inferred from the verb rather than stated.

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 by 'adds ... to the startup's queue' and reinforced by the prerequisites (tracker:write, Autopilot plan), which tell the agent when the call can succeed. There is no explicit when-to-use versus when-not, nor a pointer to getfund_queue or getfund_search_programs for the discovery step that logically precedes this one.

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