Mosaya

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds real behavior: it returns a card, stores nothing, caps results at three, and swaps in care and crisis lines when the person's words signal crisis. That crisis-handling rule is a genuinely important behavior an agent could not infer from structured fields.

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?

Three sentences, front-loaded with what the tool returns, then when to use it, then the safety override — each sentence carries distinct information. The parenthetical practice list is slightly heavy but earns its place by defining matchable scope.

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?

With no output schema, the description still tells the agent what comes back (a card, up to three options, or a care card) and that nothing is persisted, which is everything needed to call and present results correctly. Complexity is low and the definition matches it.

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 100%, so the schema already defines both need and minutes fully; the description adds no syntax or interpretation beyond restating that the practice may be requested by name. Baseline 3 applies since the description does no extra work here.

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?

"Offer the person up to three Mosaya practices they can do right here" gives a concrete verb (offer/surface) and resource (practices), with the catalogue scoped by the parenthetical list. It is clearly a discovery/selection tool rather than a launcher, but it never names the sibling start_practice, so the boundary is inferred rather than stated.

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?

"Use when they want to meditate, calm down, settle a racing mind, sleep, focus, or ask for a practice by name" gives a rich set of triggering intents, including the name-lookup case. It stops short of an explicit exclusion or pointing to start_practice once a practice is chosen.

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, and closed-world, and the description reinforces this with "Nothing is stored," which preempts the mistaken reading that opening a practice creates a session record. It also describes the runtime experience the caller is triggering, though it says nothing about failure modes or invalid practice ids.

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-loaded with the core action, then the routing rule, then the no-persistence guarantee. The bell-and-celebration detail is mildly decorative but does convey what the user will see, so it mostly earns its place.

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 two-parameter tool with full schema coverage, annotations, and no output schema, the description covers what it does, when to invoke it, and the non-persistence guarantee. Nothing an agent needs to call it correctly is missing.

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 both parameters are already documented, including the enum and the 1–180 minute bounds. The phrase "the person picks a length" adds only light framing over the schema's own "A length the person asked for, if any," and the description never mentions the practice id sourcing beyond the find_practice hint.

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 — "Open one Mosaya practice, ready to begin" — and immediately scopes it with the runtime behavior (full screen, bell, celebration). It explicitly names the sibling find_practice, so an agent can tell the two apart without inspecting either schema.

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?

Gives a clear selection rule: use after find_practice, or when the person names a practice directly. No explicit when-not or exclusion cases are offered, but the ordering against the only sibling is unambiguous.

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