Erinys Save

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

With no annotations, the description carries the full burden and does substantial work: it documents the principal resolution chain (explicit → ERINYS_PRINCIPAL → 'unknown'), that provenance is recorded in VMG, and that writes outside allowed_projects/allowed_scopes are rejected with POLICY_DENIED while unset gates allow unconditional writes. That is real mutation-safety context. It stops short of stating whether a save with an existing topic_key overwrites, deduplicates, or errors.

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 one-line purpose is front-loaded, followed by two focused blocks on principal and the access gate; no sentence is padding. The mixed Japanese/English phrasing and embedded version labels (P0-7) add mild noise but do not obscure meaning.

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?

An output schema exists, so return values need not be explained, but for a 12-parameter write tool with zero schema descriptions the definition is not complete enough. Nine parameters, including the key identity fields topic_key and session_id, are left for the agent to guess at.

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% across 12 parameters, so the description must compensate and it largely does not. It covers only principal, allowed_projects, and allowed_scopes; title, content, type, scope, project, metadata, topic_key, session_id, and source_class are entirely undocumented, including the meaning of topic_key and source_class, which are non-obvious.

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 and resource: 'Save a structured observation to ERINYS memory.' An agent immediately knows this is the single-record write path. It does not, however, contrast itself with the very similar erinys_batch_save or erinys_update siblings, leaving the boundary implicit.

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 explains the conditional access-gate behavior (explicit arg > env > None) and the POLICY_DENIED outcome, which is useful. But it never says when to choose this tool over erinys_batch_save (multi-record) or erinys_update (mutating an existing memory), so selection among siblings is left to inference.

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