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

Annotations already declare this as a non-read-only, non-destructive, idempotent, open-world write. The description adds genuinely complementary context: the optimistic-concurrency model (expected_version must match current version on edits) and the required provenance fields (source contribution IDs, reason). It does not explain permissions, failure modes on version conflicts, or what a successful save returns.

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?

Two dense sentences with no filler; the create-versus-edit distinction is placed immediately after the purpose so the caller sees the critical branch early. The first sentence is list-heavy but each element (kinds, source IDs, reason) is required information.

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 9-parameter, 8-required write tool with no output schema and 11% schema coverage, the description leaves meaningful gaps: it never explains what 'key' identifies, what 'client_id' is for, or how 'title' and 'content' relate to the record. An agent could invoke it, but would be guessing on several required fields.

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 only 11%, so the description has to carry most of the parameter burden. It does explain source_ids, reason, memory_id and expected_version semantics, but leaves 'key', 'client_id', 'title' and 'content' entirely undefined in both schema and description; the kind enum is self-documenting. Partial compensation, so a mid-tier score.

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 pair ('Offer or revise') and the resource ('shared artifact, story, question, observation or tradition'), so the write intent is unmistakable. It implicitly separates this from the read-only 'read_shared_memory' sibling, but never names an alternative or explicitly contrasts with other write siblings like submit_public_post or submit_draft.

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?

Gives concrete mode-selection guidance: expected_version:0 creates, while editing requires memory_id plus the current expected version. That is real when-to-use information for the caller's main branch decision. It stops short of any when-not-to-use or sibling routing advice.

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