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

Annotations already declare read-only, non-destructive, closed-world behavior, and the description stays consistent by clarifying that BLAST is not run internally but supplied as blast_csv. Beyond the annotations it discloses real behavioral traits: targets are packed non-overlapping from the 3' end, each target is two arms of arm_length, and junction specificity is silently skipped when blast_csv is absent.

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?

One front-loaded sentence with the verb and domain first and the four pipeline stages following in execution order; nothing is filler. It is dense and slightly run-on, which makes it harder to scan than a short bulleted pipeline would be, but no sentence is wasted.

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 an 11-parameter tool with an output schema, the description supplies what the schema cannot: the ordering of the design steps, the external blastn invocation parameters the user must produce, and the consequence of omitting blast_csv. Combined with full schema coverage and explicit annotations, an agent has everything needed to invoke it correctly.

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 tying several parameters to mechanism rather than restating them — the Tm 'window' (min_tm/max_tm), 'two-arm targets' (arm_length), 'non-overlapping ... from the 3' end' (interval), and 'the backbone given' (linkers/barcode). It does not explain the _subject/_files record shorthands or the variants scope, which remain schema-only.

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 opens with a specific verb+resource ('Design padlock probes for in-situ sequencing') and then enumerates the exact sub-tasks performed: Tm filtering, junction-specificity screening, 3'-anchored non-overlapping packing, and backbone assembly. It is clearly distinct from generic primer design tools, though it never names the close siblings (design_ish_probes, design_merfish_probes, design_xenium_probes, design_hcr_probes) to disambiguate.

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 only implied through the described pipeline: the agent can infer that a subject transcript set plus a precomputed blastn run is needed, and there is one explicit conditional ('Without it no target is checked for junction specificity'). There is no statement of when to choose this over the other in-situ probe designers, and no mention that _subject must effectively be supplied despite zero required parameters.

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