share_findings

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

With no annotations, the description takes on full disclosure. It reveals that content is secret-scrubbed, stamped with session/date provenance, indexed, lower-confidence, never displaces user-written memory, counts against retention, and is strictly per-workspace. This goes far beyond basic operational details and sets accurate expectations for side effects and security.

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 longer than average but each section earns its place. It is well-structured, front-loading the main purpose, and then methodically covering when, how, behavioral implications, permission, and parameter semantics. A few redundant phrases (e.g., 'durable, searchable memory' and 'indexed for search') prevent a perfect score, but it is far from wasteful.

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?

Given no output schema and no annotations, the description covers all needed context: purpose, usage timing, permission requirements, pipeline behavior, retention, discoverability, and parameters. An agent would be fully equipped to decide when and how to invoke this tool.

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?

The input schema already describes all three parameters with high coverage (100%). The description essentially restates the schema's parameter details (e.g., summary is a one- or two-line headline, paths are globs). It adds a small example for paths but nothing conceptually new, so the schema remains the primary source of truth. Baseline 3 is appropriate.

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 opens with a specific, vivid action: 'Hand off what you have just learned to other agents on this workspace as a durable, searchable memory'. It clearly differentiates from siblings (e.g., 'instead of waiting for the idle summary') and identifies the resource (agent-generated memory) and the expected outcome. It also contrasts with user-written memory, which removes ambiguity.

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?

Explicit when-to-use guidance is provided: 'Use it after you have mapped a subsystem, pinned down a gotcha, or worked out how something fits together'. It also gives a when-not-to-use by saying 'instead of waiting for the idle summary to fire', and includes a hard prerequisite ('Requires [collab] knowledge_handoff = true'). This effectively covers both timing and alternatives.

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