Pally

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

Annotations already cover safety (readOnly, non-destructive, closed-world), and the description adds genuinely useful context above that bar: what the return contains (reply or recap) and how to render it (verbatim vs. paraphrased with facts, links, and questions preserved). It omits whether the call blocks or what happens if the turn is still unresolved, which is a real gap for a 'check' tool.

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, zero boilerplate: the first defines what is collected, the second defines the output handling rule. Front-loaded and every clause carries information.

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?

No output schema exists, so the description usefully compensates by describing the payload (reply or recap) and the presentation contract. What remains unaddressed is the pending/not-ready state and failure mode, which matters for a name like check_pally.

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?

With one parameter at 100% schema coverage, the schema already documents turn_id's source and the omit-to-get-newest behavior. The description adds no syntax, format, or lifecycle detail beyond that, so baseline 3 applies.

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 (collect) and two concrete resources (a pending Pally turn's reply, or a call recap from start_call), which lets an agent distinguish it from message_pally. It never explicitly contrasts itself with sending a new message, so the sibling differentiation is implied 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?

Names the trigger condition clearly: use it when a turn 'was still working' or to fetch a call recap. It also encodes the alternative path implicitly via turn_id's source (message_pally or start_call). There is no explicit 'do not poll repeatedly' or 'use message_pally instead when starting a new turn' exclusion.

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 only declare it is not read-only, not destructive, and open-world; the description adds the behavior that actually matters: replies must be presented verbatim as the entire response, tasks are written in plain words with full detail, and the operation can be asynchronous, returning a turn_id to poll via check_pally. That is substantive context beyond the annotation set.

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?

Four sentences, none wasteful, with the core purpose and scope front-loaded before the usage and output-handling rules. Slightly dense but every clause carries an instruction the caller needs.

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?

No output schema exists, so the description compensates by stating how to handle the return (verbatim presentation, use in the answer, turn_id polling). Its scope enumeration, async fallback, and single-param contract make it complete enough to invoke correctly.

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?

Only one parameter, and the schema already documents it at 100% coverage with essentially the same wording. The description adds a nuance the schema does not: when relaying conversation, pass the user's words unchanged rather than paraphrasing, versus writing a detailed task when delegating. Marginal but real added meaning.

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 (ask) and resource (Pally, the user's personal assistant) and enumerates the domains it covers: messages, email, calendar, contacts, reminders, memory, calls, bookings, purchases. It also implicitly distinguishes itself from the sibling check_pally by handling the 'still working' case through that sibling.

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?

Explicit guidance on when to use it (anything needing the user's Pally-connected data), when to relay user words verbatim, when to write a plain-words task, and the exact fallback: 'If Pally is still working, call check_pally with the returned turn_id.' The alternative and the condition that selects it are both named.

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?

Goes well beyond annotations (readOnlyHint=false, openWorldHint=true) by disclosing that it returns a call link which must be handed to the user, and that a recap becomes available afterwards via check_pally with turn_id. Doesn't cover cost, permissions, or failure modes, keeping it short of a 5.

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 action and trigger, then return value, then follow-up. The sentence about the call view ('or in the call view when the app shows one') is slightly redundant padding but everything else 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?

With no params and no output schema, the description covers initiation, the returned artifact, how the user completes the interaction, and the post-call recap path — enough for an agent to call it and handle the result correctly.

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?

Zero parameters, so baseline is 4; the description usefully documents the output value (call link) and the turn_id that must be passed to check_pally, which the absent output schema would otherwise leave unexplained.

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 ('Start a live voice call between the user and Pally') and the trigger conditions distinguish it from message_pally and check_pally immediately.

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?

Explicitly says when to use it (user wants to talk live/by voice or asks to call Pally) and names the alternative path ('to have Pally ring the user's phone instead, ask Pally through message_pally'), plus the follow-up tool check_pally for the recap.

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