Joy2Move Home Exercise Library

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

Annotations already declare a safe read (readOnly, idempotent, closed-world), but the description adds real behavioral context: a 15-second Mux clip, up to five newest confirmed workout appearances, no separate YouTube demo, and the fact that start_seconds already includes the four-second lead-in. The 'do not claim clinical or technique certification' constraint and the video_status fallback are exactly the kind of policy disclosure annotations cannot 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 identity and provenance of the lookup, then moves to return contents and operating constraints. Every sentence carries information, though the video/YouTube sentences are dense output-field detail that reads slightly list-like.

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?

There is no output schema, so the description must describe returns itself — and it does, naming equipment, the video segment, workout appearances, full_video_url and video_status. Combined with the fallback behavior and the exact-slug acquisition rule, an agent has everything needed to call it and present results honestly.

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?

The schema has 0% description coverage on the single slug parameter, so the description must compensate. It does so by specifying the slug is the *exact* one from search_exercises, which tells the agent where to obtain a valid value rather than inventing one, though it does not restate the lowercase-hyphen format the schema pattern enforces.

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 (get) and resource (a catalog exercise) and states the lookup key is an exact slug sourced from search_exercises. That explicitly distinguishes it from its only sibling, which is a search rather than a lookup.

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?

Routes the agent to search_exercises as the source of the slug and gives an explicit fallback branch for when video_status is unavailable. It stops short of an explicit 'do not call with a guessed name, call search_exercises first', so the boundary is strong but not fully spelled out.

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

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely non-derivable behavior: results split bodyweight vs weighted variations, empty results mean no catalog match, and the agent must not fabricate a demo. Pagination/`limit` behavior is the only gap.

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?

Five short, front-loaded sentences; each one carries a distinct instruction (search axes, query hygiene, variation handling, empty-result semantics, out-of-scope). No filler or restatement of the title.

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 5-param search tool with no output schema, the description covers intent, query discipline, result interpretation, and exclusions well. The two remaining blanks are the unmentioned `limit` parameter and the lack of an explicit handoff to the get_exercise sibling.

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 carries the burden, and it does name query, equipment, category, and muscle with useful framing (alias support like 'RDL', concise-name constraint, unspecified-equipment fallback). However `limit` is never mentioned and no format/syntax expectations are given for the free-text fields beyond brevity.

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 names a specific verb+resource ('Find exercise demonstrations') and enumerates the exact search axes: name/alias, equipment, category, muscle. It does not differentiate against the sibling get_exercise, so an agent has to infer that this is the broad search while the sibling is the single-item lookup.

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?

Strong contextual guidance: 'Pass a concise exercise name, not the whole user message,' the fallback behavior when equipment is unspecified, and an explicit exclusion ('Not for diagnosis or personalized injury rehabilitation'). It stops short of naming the alternative tool (get_exercise) for direct lookups, which is the one routing decision left to inference.

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