Keep a file with a task or in a document

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

With no annotations, the description carries the full burden and does: it discloses that the file is copied rather than linked, that doc attachments land at the end, that task attachments record provenance, the 650 MB ceiling for both targets, and the special `.html`/`.htm` widget rendering plus how to opt out via the `"file"` title. That is exactly the non-obvious behavior an agent could not infer from the schema.

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 core behavior and the mutually-exclusive destination rule are front-loaded, which is correct. The single dense paragraph stacks several nested clauses around the html widget fallback syntax, making it harder to scan than it needs to be, though nearly every sentence carries real 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 4-param mutation tool with no annotations and no output schema, the description covers destination semantics, size limits, copy-not-link durability, and rendering behavior. What it omits is what the tool returns (a reference string? an id?) and any failure modes beyond the size cap, which an agent would want when chaining follow-up calls.

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 coverage is 100%, so the baseline is 3; the description earns an extra point by explaining what each destination parameter actually produces (task journal entry with source noted vs. appended document element). It does not clarify `label` defaults beyond what the schema already says, so it stops short of a 5.

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 concrete verb and action ('Copy a file from this machine into Tisty') plus the two possible destinations, so the resource and scope are unmistakable. It also spells out the divergent outcomes for `task` vs `doc`, which lets an agent distinguish this from sibling tools like `write_doc` or `file_doc`.

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?

Explicitly says to name `task` OR `doc` and that it is 'One or the other, never both,' which is the key decision the caller must make. It also adds a caution ('Only attach what you were asked to') but never names a sibling alternative for when a file should not be attached this way.

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