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

With no annotations, the description carries the burden and does well: it discloses that this is a two-step propose/confirm flow, that existing tags are replaced rather than merged, and that the return value is a proposalId. It stops short of stating permission or governance requirements and whether replacing tags with an empty object clears them.

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 tight clauses, front-loaded with the action and resource, then the critical replace semantics, then the follow-up call and safety note. No wasted wording.

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 two-parameter staging tool with a nested object schema and no output schema, the description covers the action, the mutation semantics, and the return handle. Minor gaps remain around validation rules, key/count limits, and required permissions.

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 100% and both parameters are documented in-schema, so the baseline is 3. The description adds the useful "flat string key/value pairs" constraint and the replace-on-confirm behavior for metadata, but adds nothing about accountId beyond what the schema already says.

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 ("Propose updating wallet metadata tags") and immediately qualifies the resource's shape ("flat string key/value pairs"). It also states the replacement semantics on confirm, which distinguishes it from pure-read or pure-write siblings, and names confirm_proposal as the completing action.

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?

Clear context for use: you call this to stage a tag change and then call confirm_proposal to apply it, and it explicitly notes this is not a money-moving action, which helps route an agent away from transfer/swap tools. It lacks an explicit "when not to use" clause or comparison against other propose_* siblings.

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