analyze_profile

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

No annotations are provided, so the description carries the full burden. It mentions 'scoring identifies compression candidates' but doesn't disclose what side effects exist (if any), whether this is a read-only operation, whether it modifies data, rate limits, auth requirements, or what the returned analysis looks like. For a tool that computes scores and suggests deletions, the absence of explicit 'read-only/no-modification' clarification is a gap.

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 quite short and front-loaded with the core purpose. However, the mention of 'batch_operations' in the same sentence mixes usage guidance into the purpose statement, and referencing a specific sibling tool name is somewhat fragile/implementation-specific rather than describing general intent. Could be cleaner and more structured.

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?

There is no output schema, so the description should explain what the tool returns (e.g., list of entries with scores, count of candidates). The scoring model, how compression candidates are weighted, and how focus/persona/threshold interact is partially implied but never explicitly explained. For a tool with no output schema and 3 meaningful parameters, the description leaves the actual deliverable unspecified.

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% and each parameter (focus, persona, score_threshold) has a clear description including boost behavior for focus and defaults for persona/threshold. The description adds slight context by framing these as 'scoring' inputs that identify compression candidates, but the schema descriptions themselves already explain each parameter's effect well.

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 the tool analyzes a profile and identifies compression candidates via scoring, mentioning batch_operations for cleanup. However, it doesn't clearly specify what 'profile' refers to (user's full profile? a specific section?) and the verb+resource is somewhat generic ('プロフィール分析' = profile analysis) without distinguishing precisely what analysis or output it produces compared to get_stats or get_context.

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?

The description mentions combining with batch_operations but provides no explicit when-to-use or when-not-to-use guidance vs alternatives. There's no exclusion criteria, no mention of when this is preferred over get_stats, get_context, or search. A user cannot tell if this is meant for routine analysis or only for pre-cleanup surveys.

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