ypollak2/llm-router

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

No annotations provided, so description carries full burden. Discloses important behavioral details: reads from macOS Keychain, calls external Anthropic endpoint, updates local cache, and platform restriction (macOS only). Missing potential error states or rate limit details, but covers main operational mechanics well.

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 well-structured sentences: front-loaded purpose with key differentiator, mechanism explanation, and prerequisites. Zero waste—every sentence adds essential context not available in structured fields.

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?

Adequate for tool complexity despite no annotations. Covers OAuth flow, caching behavior, platform constraints, and prerequisites. Output schema exists (per context signals), so return value explanation is unnecessary. Could enhance with error condition notes, but sufficient for invocation decisions.

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?

Input schema has 0 parameters, establishing baseline 4. Description appropriately requires no parameter explanation since the tool operates with no inputs (reads from Keychain automatically).

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?

Clear verb ('Refresh') and resource ('Claude subscription usage') with specific mechanism ('via the OAuth API'). Implicitly distinguishes from siblings like llm_usage or llm_check_usage by specifying OAuth/Keychain approach and 'no browser required,' though explicit comparison to alternatives is absent.

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?

Provides prerequisite requirements ('Requires: Claude Code installed and authenticated on macOS') and implies usage context ('no browser required'). However, lacks explicit when-to-use guidance versus sibling tools like llm_update_usage or llm_track_usage, and no 'when-not' exclusions.

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