Log Favorite Song (music write)

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

Even though readOnlyHint=false already signals a write operation, the description explicitly states it MUTATES the favorite tracks list, which removes any ambiguity. It adds valuable behavior beyond annotations: authentication requirements, share-token write restrictions, and a $0.10 cost. This is exactly the kind of context annotations do not capture.

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?

The description is information-dense and front-loaded with the key action word 'MUTATES'. The example is helpful rather than padding. However, the final parenthetical '($0.10; API key required)' partially repeats the earlier 'Requires API key' statement, introducing minor redundancy. Overall itearns a 4 for efficiency with a small deduction.

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 tool with 9 parameters, no required fields, an output schema, and various potential edge cases, the description covers purpose, routing, example usage, optional parameters, authentication, restrictions, and cost. The input schema and output schema handle parameter-level and response details, so nothing essential is missing.

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 coverage is 100% so the baseline is 3, but the description adds crucial semantic meaning that the schema alone does not convey: the two acceptable input forms ('track' blob OR title+artist) and a concrete example showing the blob format. It also correctly highlights optional year_note and source_url. This goes beyond merely restating property descriptions.

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 verb 'MUTATES' plus the resource 'authenticated user favorite tracks list at /music' states exactly what the tool does. It is clearly distinguished from sibling logging tools by targeting a specific music write operation, and the title 'music write' reinforces this differentiation.

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?

'Use when they favorite or save a song — do not store this as a chat memory or in music_preferences' gives explicit when-to-use and when-not-to-use guidance. It also names alternatives (chat memory, music_preferences) and provides authentication prerequisites ('Requires API key or OAuth with scope context. Share tokens cannot write.').

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