longwatch

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

With no annotations, the description carries the full burden. It discloses return values (watch_id, key, poll URL) and type-specific processing (e.g., 8-K item codes decoded, Form 4 insider trades parsed). It does not mention side effects like immediate polling or persistence, but provides substantial behavioral context.

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 pack the core purpose, type enumerations, and return values without fluff. The description is front-loaded with 'Create a standing watch' and each clause 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 10-parameter tool with nested objects and no output schema, the description covers each watch type's core behavior and the return shape. It does not explain parameter interdependencies (e.g., above/below/move_pct_24h), but the schema handles those details.

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 the baseline is 3. The description adds meaningful semantics by explaining what each watch type watches and how the type parameters map to behaviors (e.g., 'crypto threshold/24h-move via CoinGecko id'), exceeding the schema's property descriptions.

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?

Clearly states 'Create a standing watch' and then enumerates the four watch types with their specific monitoring semantics (url text diff, rss new items, price via CoinGecko, SEC filings with parsed Form 4 trades). This distinguishes it sharply from siblings delete_watch and poll_alerts.

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?

The description implicitly conveys usage through type-specific explanations, and the sibling names (delete_watch, poll_alerts) make the operation context obvious. However, it does not explicitly state when not to use this tool or provide alternative selection guidance.

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?

With no annotations, the description must disclose destructive behavior. It says 'delete' and 'Free', implying resource removal, but does not mention irreversibility, permission requirements, or downstream effects on associated alerts. Minimal behavioral disclosure.

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 description is extremely concise with two short sentences. The key purpose is front-loaded, and no unnecessary elaboration or redundant content is present.

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 simple deletion tool with two well-described parameters and no output schema, the description covers the basic purpose. However, it lacks usage context and behavioral details, making it adequate but not fully complete for an agent operating without annotations.

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 covers both parameters with clear descriptions (key from create_watch, watch_id to delete), giving 100% coverage. The description adds no additional parameter semantics, so baseline 3 is appropriate.

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 clearly states the action ('Stop and delete a watch') with a specific verb and resource. It distinguishes itself from siblings create_watch and poll_alerts by focusing on deletion and resource release ('Free').

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, contextual triggers, or exclusions, leaving the agent without decision support.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the cursor and that polling keeps the watch alive, but does not explain key behavioral aspects such as the response format (whether alerts are included), the effect of omitting 'since', or whether polling is blocking. This is a significant gap for a polling 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?

The description is concise: two sentences with no fluff. The first sentence states the core action, and the second provides essential context about the cursor and watch lifecycle. Every sentence 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?

Given the tool's complexity (3 params, no output schema, no annotations), the description covers the essential cursor-based polling concept but misses important details such as the response content (does it include the alerts themselves?), default behavior when 'since' is omitted, and potential error conditions. It is minimally adequate but leaves gaps for an agent to fill.

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 descriptions already cover 100% of the parameters with clear explanations (e.g., 'since' is described as 'highest alert seq already seen; 0 on first poll'). The description adds marginal value by reinforcing the use of 'since' and noting the response carries a new cursor, but it does not substantially enhance understanding beyond the schema.

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 clearly states the action: "Poll a watch for alerts since a cursor." This uses a specific verb (poll) and resource (watch for alerts), and it distinguishes itself from sibling tools (create_watch and delete_watch) by its focus on retrieving alerts rather than creating or deleting a watch.

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?

The description provides context for when to use this tool: it explains the cursor mechanism and states that "Polling keeps the watch alive," implying this tool is used periodically to receive alerts and maintain the watch. However, it does not explicitly contrast with create/delete or state when not to use it, so it falls short of a perfect score.

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