mpfb_get_expression

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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds substantial context beyond them: unresolvable rows contribute nothing to the face, matches_stack false means composed work that the next apply/preset load will overwrite while mpfb_save_expression keeps it, and an unresolvable subject yields found:false rather than an error. This is rich behavioral disclosure that the annotations do not 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?

Front-loads the purpose well, but the bulk of the text re-describes output-schema fields (applied_expressions rows, aggregate, clamped_face_units, matches_stack, unexplained_face_units) that the output schema already carries. That duplication dilutes conciseness for a two-parameter getter.

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 an output schema exists, the description goes beyond requirement by narrating return values and edge cases (unresolved_count, found:false, basemesh_name), which makes it complete for the read operation. The only gap is the 'name' parameter's meaning, which neither description nor schema clarifies.

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 0%, so the description must compensate. It explains 'refresh' ('re-probes for it') but gives no explicit meaning for 'name' as a parameter – it only indirectly implies the subject via 'An unresolvable subject is found: false'. Partial compensation warrants a baseline 3.

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?

States a specific verb and resource ('Read which saved expressions a MakeHuman character is wearing') and scopes it to the applied-expressions stack. It also explicitly differentiates itself from a sibling ('For the raw live face-unit values, call mpfb_get_face_units; this tool reports only how they differ from the stack').

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?

Names the alternative tool (mpfb_get_face_units) and the condition that selects it, and clarifies the scope difference from the raw live values. It also places the tool within a workflow by naming mpfb_set_face_units, mpfb_apply_expressions and mpfb_save_expression as the things that touch the 'composed work'. No explicit when-not beyond the alternative, so it falls short of 5.

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