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

Annotations only declare it is a non-destructive, non-idempotent write, so the description's additions are genuinely useful: it warns 'Never include personal data' and discloses the side-effect rule that agent wishes do not count toward human shrine progress. It still omits what actually happens to the wish after submission (visibility, storage, reversibility), but it substantially augments the annotation profile.

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 compact sentences, front-loaded with the core action and no filler. The privacy warning and the progress caveat each carry distinct information, so little is wasted, though the opening clause is slightly redundant with the tool name.

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 single-parameter tool with annotations covering safety and no output schema, the description covers content expectations and privacy adequately. It is incomplete on outcome: an agent cannot tell whether the wish is stored, published, or merely echoed, which matters for a write tool whose only annotation is that it is non-destructive.

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?

With one parameter at 0% schema description coverage, the description must carry the meaning of 'text'. It does partially: 'in your own words' and 'Never include personal data' tell the agent what kind of content is expected, but it never mentions the 500-character limit or the format expectations the schema enforces.

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 essentially restates the tool name ('Make a private wish') and then defines the flavor of a wish ('a hope, a regret, or something you'd like to let go of'), which clarifies intent but not the underlying operation. It never distinguishes itself from siblings like draw_oracle, light_incense, or register, so an agent gets the vibe but not a crisp verb+resource statement.

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 or when-not-to-use guidance relative to the sibling tools. The note that 'agent wishes never count toward human shrine progress' hints at a usage context (agents may record wishes that do not affect shrine state), but it reads as a caveat rather than routing guidance between alternatives.

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