speaker_profile_save

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions the tool creates a plan (not a direct save) and is deprecated, but does not explain what 'hash-bound' means, side effects, prerequisites, or how the plan is consumed. This is minimal for an operation with a complex profile object.

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 a single sentence that front-loads the deprecation and names the execution counterpart. It is efficient and avoids redundancy, though the unexplained 'hash-bound' term could confuse and costs a bit of clarity. Overall it earns its place.

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?

Despite the complexity of the nested profile object and the absence of annotations and output schema, the description is very short. It does not explain the purpose of the plan, the meaning of 'hash-bound', or the overall save flow beyond separating plan and execution. Critical information for correctly invoking the tool 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 description coverage is 0%, so the description must compensate for explaining the parameters. It does not mention 'profile' or 'home' at all, nor what they represent or how they relate to the 'hash-bound' plan. The schema provides structure but no semantic meaning, leaving the agent to guess.

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 creates a speaker-profile save plan and directs execution to speaker_profile_save_execute. It clearly distinguishes itself from the execute tool, though it does not explicitly name speaker_profile_save_plan as the canonical alias. The term 'hash-bound' and the deprecation flag add some ambiguity but the core purpose is conveyed.

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 marks the tool as a 'deprecated compatibility alias', telling the agent to prefer newer alternatives, and specifies the two-step workflow (create plan, then execute). It does not explicitly say 'use speaker_profile_save_plan instead', but the deprecation and the pointer to the execute tool give clear usage context.

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