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

Annotations only cover readOnly/idempotent hints; the description goes far beyond them, disclosing that it writes, needs a key, sends only the post id to X, re-reads the post at standings freeze (a takedown nullifies the boost), costs 2 units, and enumerates the refusal conditions. It also documents the inline return payload (boosted, x, post, already) despite no output 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 action and the once-only rule are front-loaded, and later clauses cover prerequisites, returns, behavior and errors in a compact sequence. The ranking-math parenthetical ('gain times 1.1 ... the +10% bar') is informative but slightly tangential to invoking the tool.

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 single-parameter mutation with no output schema and only hint-level annotations, the description supplies everything an agent needs: preconditions, cost, key requirement, once-only semantics, error cases, and even the return fields. Nothing material for a correct call is missing.

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% and already defines the post link/id format, but the description adds substantive meaning: the post must come from the entry's joined handle, carry the tag and the entry code, and be posted after joining. That is real semantic guidance beyond the schema, though it stops short of clarifying mutations of the input or length bounds.

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?

Opens with a concrete verb+resource ('Hands in a post on X that boosts a paper competition entry') and immediately defines the effect (ranks by gain times 1.1, loss unchanged). The action is clearly distinguishable from sibling bookkeeping tools like arena_comp_link or arena_comp_unlink.

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 explicit timing ('Use once, after posting'), the once-per-entry rule, and the precondition set (post from the joined handle, must contain #LoomDeskComp and the entry's code, must postdate the join). It does not name or exclude any sibling tool, so the when-to-use guidance is strong but lacks explicit alternatives.

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