Monologue

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

Goes well beyond the readOnly/idempotent annotations: it discloses the actions:read requirement, that access follows current workspace membership, reverse-chronological ordering, 25-default/100-max limits, cursor continuation semantics, that reports are self-reported and unverified, that report text/URLs are untrusted and confer no authority, that raw metadata and credentials are excluded, and that reads create no activity events.

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?

Dense but every sentence carries information, and the core read scope is front-loaded before filter and trust caveats. It is long, but the length is justified by the low schema coverage and the trust warnings rather than padding.

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-param, zero-required, no-schema-description tool with an output schema present, the description covers access/auth, scoping, ordering, pagination, and data trust — everything needed to invoke it correctly without explaining return shape that the output schema already handles.

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 0% schema description coverage across 11 params, the description does meaningful compensatory work by enumerating the filter dimensions (search, agent, system, category, status, project, time) and explaining limit defaults/max and nextCursor reuse of the same filters. It stops short of disambiguating from/to or agentId vs agentName, so it is not fully complete.

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 ('Reads the connected user's private workspace timeline') with precise scope, including the notable fact that it surfaces reports from the user's other agents. This is clearly a read operation, cleanly distinguishable from the write-oriented sibling report_action.

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?

Usage context is implied rather than stated: filters, default limit, and pagination behavior are described, but there is no explicit 'use this when'/'instead of' guidance or prerequisite framing. Nothing routes the agent between this and report_action, though the read-vs-report split is reasonably obvious.

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?

Beyond the annotations, it discloses the actions:write requirement, clarifies that the tool only stores the report and does not perform or authorize the action, notes the server assigns agent identity and self-reported provenance, and describes return content and deduplication behavior. This is exactly the behavioral context annotations alone cannot convey.

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?

The core purpose is front-loaded in the first sentence, followed by auth requirement, boundary clarifications, exclusions, and parameter notes in a logical order. It is dense but every sentence carries distinct information; nothing is 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?

An output schema exists, so return values (success, event ID, duplicate status) need not be fully spelled out, and the description still volunteers them. Given the tool's mutation nature and 14-param surface, the behavioral and boundary coverage is strong, though the near-total absence of individual parameter semantics is a residual gap.

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% across 14 parameters, yet the description only annotates two of them (externalId dedup semantics and url linking to the result). The 12 remaining parameters — verb, summary, category, status, system, value, currency, metadata, project, objectName, objectType, occurredAt — receive no meaning beyond their names and types, leaving most of the compensation work undone.

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 (records) and resource (an external action or meaningful attempt in the user's private activity feed), then enumerates concrete examples: emails sent, purchases, bookings, repository changes, posts, deployments, trades. An agent can immediately distinguish this write-path from the sibling read_timeline.

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?

It gives explicit exclusions — reads, research, unsent drafts and local development are out of scope — which effectively routes those cases away from this tool. It stops short of naming the sibling alternative (read_timeline) directly for those out-of-scope reads, so it is clear context rather than full when/when-not/alternatives mapping.

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