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

Goes well beyond the destructiveHint/idempotentHint annotations by disclosing what actually gets destroyed and its downstream semantics: the deletion persists even when the source piece is re-read, and in a shared brain it removes the memory for every voice. It also adds an interactive safety requirement (user confirmation), which is exactly the kind of context annotations cannot express.

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 short sentences with no filler; the core action leads, and each following sentence adds a distinct behavioral fact (persistence, blast radius, confirmation). Nothing is redundant with the annotations.

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 two-parameter, no-output-schema tool, this covers purpose, irreversibility semantics, cross-voice impact, and a safety step. The only meaningful gap is the unexplained profile_id, which the agent must infer or obtain elsewhere.

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 carry parameter meaning. It explains unit_id's provenance ('unit_id from get_memory'), which is genuinely useful, but profile_id is never mentioned, leaving one of two required parameters undocumented.

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?

States a specific verb (delete) and scoped resource ('one memory'), and points at get_memory as the source of the id, which helps the agent distinguish deletion from retrieval. It does not, however, differentiate from the more confusable siblings edit_memory or forget_piece, so sibling selection still requires inference.

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 purpose plus the procedural directive 'Confirm with the user first', which is a real prerequisite. But it never states when to choose this over edit_memory (modify) or forget_piece, so guidance on alternatives is absent.

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