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

Beyond the readOnly/idempotent/closed-world annotations, the description discloses substantial behavior: statements naming a paper are withheld unless a citation and a selected retained excerpt accompany them, exported citations and BibTeX/RIS entries are validated one-to-one, and exact matching explicitly does NOT authenticate imported reports or verify semantic support. The privacy/retention caveat about the MCP client also adds operational context annotations cannot carry.

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?

Purpose is front-loaded and each sentence carries real content: withholding rule, one-to-one validation, matching caveat, I/O boundary, retention note. It is dense and jargon-heavy ("Include paper records," "Keryx report rows"), which slows parsing, but there is little outright filler.

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?

With no output schema, the description must convey what comes back, and it does: an exported draft/citations with a defined withholding and validation behavior, plus a note that the returned draft may be retained client-side. Combined with 100% parameter coverage, an agent has enough to invoke it correctly, though the return structure itself remains abstract.

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 100% and there is only one parameter, so the baseline is 3. The description elaborates on what is assembled and mentions "caller-supplied" inputs, but it does not add format or contract detail for the `draft` parameter beyond what the schema already documents (byte limit, append/regenerate modes, readingStatuses).

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 names a specific verb ("Assemble") and clearly scopes the resource: a private retained-evidence draft built from claim spans, quote themes, saved Include paper records, and caller-supplied Keryx report rows. An agent can tell this is an assembly/composition step rather than a fetch or check, though no sibling (e.g. draft_check, evidence_procurement) is named to sharpen the boundary.

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?

Usage is implied through negative constraints — "No fetching, model, database, history, payment or reward I/O" — which indirectly steers an agent away from evidence_procurement or history_* tools when those I/O classes are needed. However, there is no explicit "use this when / not when" statement and no alternative tool is named, leaving routing to inference.

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