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

Annotations already declare readOnlyHint/openWorldHint=false, so the safety profile is covered; the description goes further by disclosing the rejection criteria (C/G runs, hairpin, G+C and RNA:DNA free-energy windows, genome hits), the non-overlap and ranking rule, and notably what happens when alignment_sam is omitted and that the result self-reports it. That conditional-degradation note is genuinely useful behavior beyond the annotations. It stops short of stating runtime cost or output volume, so a 4 rather than a 5.

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 in the first four words, then the colon-and-list structure walks the pipeline in execution order with no filler sentences. The single sentence is long and dense enough that an agent must parse a nested list, which keeps it off a 5.

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 17-parameter, nested-object tool with an output schema and read-only annotations, the description covers the algorithm end to end plus the one behavioral fork that matters (missing alignment). The _subject resolution rules and channel semantics are already documented in the schema, so nothing an agent needs before invoking is absent.

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, but the description ties the parameters into a coherent narrative — 52 nt tiling, 2 nt gap, run/hairpin/free-energy filters, target free energy for ranking, amplifier initiator — which tells the agent how the knobs interact rather than just what each means. That is meaning added on top of the per-parameter descriptions.

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?

Names a specific verb and resource — 'Design HCR v3.0 split-initiator probe pairs' — and then spells out the exact operation: tiling the reverse complement, filtering, ranking, and splitting around a 2 nt gap. An agent can distinguish this from design_ish_probes, design_merfish_probes, or design_xenium_probes on the HCR v3.0 split-initiator specificity alone, without opening any 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?

The description explains the pipeline's internal mechanics but never states when to choose this tool over a sibling probe-design tool, nor any prerequisites or exclusions. The only conditional guidance is parameter-level (alignment_sam: 'Without it no tile is checked for uniqueness and the result says so') and channel multiplexing. Usage is implied by the tool name rather than argued.

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