newswake

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

With no annotations, the description carries the behavioral disclosure burden, and it does so well. It discloses freshness ('~2h behind live'), coverage ('~296 mainstream sources'), and output nature ('signals + links only'), plus per-item fields and the 'act now vs window closing' runway hint. This gives the agent a realistic sense of latency, scope, and output limitations, though rate limits or exact update mechanics are not covered.

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 dense but efficient: value proposition, result fields, intended decision context, and data caveats are packed into a compact paragraph with no filler. The most distinctive information ('ACCELERATING right now') is front-loaded, and every clause contributes. This is a model of concise, useful tool documentation.

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 read-style list tool with no output schema, the description adequately explains return values and data limitations, and the input schema fully covers the two parameters. The only notable missing piece is guidance on how this relates to sibling whats_changed, but the tool's own purpose and results are clear enough to call it correctly. Overall it is complete for practical agent use.

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 baseline is 3: the schema already documents limit with min/max/default and topic with examples. The description adds only the general sense of 'optionally scoped to a beat/topic' and a ranked list, which does not materially improve on the schema. There is no additional parameter syntax, interaction, or defaulting nuance.

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 opens with a crisp value proposition: it identifies news 'ACCELERATING right now' as a ranked list of story-events 'climbing in attention', optionally scoped to a beat/topic. This makes the tool's purpose and resource clear and distinguishes it from a generic news or recent-changes tool, even without naming the sibling. The verbs and result fields ('trend, momentum, acceleration, outlet count...') make the function concrete.

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 explicitly tells the agent when to use it: 'Use to decide what to ride/publish/watch.' It also clarifies scoping ('optionally scoped to a beat/topic') and the signal-only nature of results. However, it does not contrast with sibling tool whats_changed or state when not to use it, so the routing guidance is good but not fully explicit.

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 discloses that the tool is stateful, that it returns signals and links only (not full articles), and that it draws from ~296 mainstream sources. It does not mention rate limits, pagination, or authentication, but it provides meaningful behavioral context beyond a minimal definition.

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 three tightly packed sentences with no redundant phrasing. The core concept is front-loaded, the return contents are specified, and the stateful-vs-stateless context and source count are appended in an efficient, useful way. 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 absence of an output schema and annotations, the description compensates well by naming all major return categories (new vs updated story-events, trend, importance, links) and specifying scope (mainstream sources, signals+links only). The two parameters are fully schema-documented, and the description provides enough context for an agent to invoke the tool 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?

Both parameters are already fully documented in the schema with descriptions, examples, and defaults, so schema coverage is 100%. The description echoes 'entity' and 'since a given time' but adds no extra parameter-level detail beyond what the schema already provides. This meets the baseline for high schema coverage.

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 identifies the tool's resource as 'the DELTA on an entity' in news coverage and specifies exactly what it returns: new vs updated story-events, trend, importance, and links. It also distinguishes itself from stateless search tools through the stateful 'what changed since my last check' framing, which separates it conceptually from siblings like find_trending.

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 gives strong contextual guidance: this tool answers 'what changed since my last check' and is positioned as something stateless search tools cannot answer. However, it does not explicitly name any sibling tool or state concrete when-not-to-use conditions, so the routing guidance is clear but not fully explicit.

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