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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety needs no restating. Beyond that, the description adds real context: the UTC-day window, the required `user` scope, and the reason for excluding canary tokens (they never authenticate), which prevents an agent from expecting them in results.

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 sentences with the primary purpose front-loaded, followed by the exclusion rule and the return shape. It is dense but nothing is filler; the inline return-shape spec is long yet earns its place because no output schema exists.

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 zero-parameter read tool with no output schema, the description supplies everything needed: the time window, the auth scope prerequisite, the documented exclusion, and a field-by-field account of the return object including edge semantics like bucketCents 0 = no bucket and suspended accounting fields.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The description does not waste space restating parameters that do not exist.

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 states a specific verb and resource ('Today's model spend (UTC day)... and the state of every personal access token of yours') and anchors it to the UI surface (/settings/tokens/spend). It clearly differs from merjax_list_tokens and merjax_ai_cost_summary in substance, though it never names those siblings to make the distinction explicit.

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 the scope statements ('Today', 'UTC day', 'of yours') and by the explicit exclusion of canary tokens with a reason. However, there is no explicit when-to-use guidance and no routing to alternatives such as merjax_list_tokens for token inventory or merjax_ai_cost_summary for broader cost views.

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