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

Annotations already flag a non-read-only, non-idempotent, non-destructive write, and the description adds real value with the ten-item cap, the consent rule, and the makeable/someday modeling rules. However, it never resolves the most important behavioral ambiguity for a non-idempotent write: whether the call appends to an existing list or replaces it, and what happens on duplicate wishes. That gap matters more than the return format, which needs no explanation given there is no output schema.

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 dense sentences, each carrying distinct rules, with the cap and resource front-loaded. Some phrasing is domain jargon ('Unfactory', 'lane') that a fresh agent must parse from context, but no sentence is redundant.

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?

For a mutation with nested wish objects, an enum source, and no output schema, the definition covers most decision-relevant rules and needs no return-value explanation. Completeness is undercut by the unexplained required wish_token and the unstated append-vs-replace semantics, both of which an agent needs before calling 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?

The description adds substantial meaning to nested fields the flat schema barely covers: it defines the three source values, explains makeable_id vs. its absence, and links lane 'someday' to closest_makeable_id/closest_idea. But wish_token is required and is never mentioned anywhere in the description or in a schema description, and the top-level source is only explained indirectly through examples.

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 opens with a specific verb and resource: 'Save up to ten wishes to the person's wish list', and clarifies what the list is. It is clearly distinguishable from read-oriented siblings like my_wishes and most_wished, though it never names the closest sibling (make_wish) to draw the boundary 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?

Strong conditional guidance: which source value applies to which situation, when to supply makeable_id versus omit it for unmakeable physical things, when to use lane 'someday' with a closest makeable substitute, and a consent precondition ('Only add what the person has agreed to'). It stops short of naming alternatives such as make_wish or start_three_wishes, so the agent must infer the routing.

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