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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does so comprehensively: it reveals that it repeats a review, treats requester limits as hard constraints, and explicitly lists a long set of actions it never performs. It also discloses the reference-only status of computed-crystal evidence and the ineligibility of placeholder values. This is exceptionally transparent for a tool with no annotation support.

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 description is a single well-structured paragraph that front-loads the core purpose, then systematically covers constraints, evidence rules, and non-goals. Every sentence earns its place—no filler, no repetition. The use of explicit 'never' statements is an efficient way to communicate boundaries without extra prose.

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?

Given the tool's complexity (7 parameters, nested structures, optional evidence) and the existence of an output schema, the description is largely complete. It covers input constraints, evidence eligibility, and non-goals. The only minor omission is the nature of simulation_handoff, but it likely refers to a predefined handoff object; the description still gives enough to call the tool correctly. The output is presumably covered by the output schema.

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 only 14%, so the description must compensate. It does: it explains the requirement must state load model, geometry, load, and elastic modulus; objectives must be stated; source freshness must be provided; physical validation plan is required. It gives detailed meaning to material_property_evidence (must match requirement, placeholder values ineligible, computed-crystal is reference-only). It does not explain simulation_handoff or candidate_id, but these are largely self-explanatory. Overall, it adds substantial meaning beyond the schema.

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 ('Compile') and resource ('prepared bounded beam simulation study'), and clarifies it operates on 'one caller-selected domain-solutioning candidate'. It distinguishes from siblings by explicitly listing non-goals ('never verifies a source claim, selects a candidate, invents physics, runs a solver, stores data, contacts a supplier, or grants physical authority'). No ambiguity about what the tool does.

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 specifies when to use it: after 'repeating deterministic engineering review' and for a single candidate. It lists required input content (load model, geometry, load, elastic modulus; objectives; source freshness; physical validation plan) and notes what it does not do, which indirectly points to alternatives like run_bounded_simulation_study. It could be even more explicit about naming alternative tools, but the context is sufficient for an agent to infer selection criteria.

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