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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the description's main contribution is the partial-update contract — 'send only what changes' — which is the non-obvious behaviour an agent needs. It stops short of stating what happens to omitted fields, whether changing edb_exercise_id resets other values, or what permissions are required.

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?

Two sentences, both earning their place: the first defines the operation and scope, the second gives the key calling instruction. Front-loaded with the edit target and zero filler.

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 mutation tool with no output schema, the description covers purpose and patch semantics but leaves several agent-relevant questions open: whether the updated exercise is returned, whether reps/reps_max interact, and what prerequisites (program ownership) apply. Adequate, but thin for the parameter surface.

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 only 45%, and the description usefully compensates by naming the undocumented fields (sets, reps, notes, rest) and mapping plain-language 'load' to weight and 'range' to reps_max. It does not mention name, phase (the only enum), or duration_seconds, so the gap is narrowed but not closed.

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 (changes), a specific resource (one exercise already in a program), and enumerates the mutable attributes (sets, reps/range, load, rest, notes). The phrase 'one exercise already in a program, without recreating the program' separates it from the coarser-grained siblings update_program, update_program_day and update_program_week.

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?

'Send only what changes' tells the agent this is a targeted edit rather than a full replace, and 'without recreating the program' implies using this instead of update_program. No sibling is named explicitly and there are no when-not-to-use conditions (e.g., adding a new exercise belongs to add_exercise_to_program_day).

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