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

Annotations only cover the generic profile (non-read-only, open-world, non-idempotent, non-destructive); the description adds the crucial two-phase protocol (returns evidence_id + upload URL, bytes sent separately via shell) and a retention/privacy guarantee ("Analyzed for that task only, never kept as a memory"). It does not disclose size limits, expiry of the upload URL, or failure behavior, which matters for a non-idempotent upload.

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 tightly packed sentences with zero filler, ordered as purpose → mechanical protocol → retention rule, front-loading the identifying information. No sentence could be removed without losing signal.

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 multi-step upload tool with an output schema, the description covers the return contract, the client-side upload step, and downstream consumption, which is what an agent most needs. Remaining gaps (accepted formats/size caps, clone_id usage) are partially covered by the schema's enum and clone_id description.

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 25% (only clone_id is documented), and the description adds no meaning for filename, content_type (a 30-value enum) or file_size_bytes beyond vaguely referencing "the file's bytes". With low coverage the description should compensate; it does not.

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 ("Share a screenshot, recording or audio clip of the work") plus the audience ("privately with the owner's consciousness") and explicitly contrasts with sibling remember by saying it is "never kept as a memory". An agent can distinguish this from remember/review_work without opening the schema.

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 the downstream path explicitly: after uploading, "pass evidence_ids to review_work or consult_mind", which names the alternatives and their ordering. It does not state the converse (when to use remember instead of share_evidence), so exclusion guidance is only implied by the retention sentence.

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