Persimmon

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

With no annotations, the description carries the transparency burden. It discloses that only public-citable signals are returned, internal-only items are filtered out, and a coverage_status field always explains empty lists. It also reveals the signal structure. This goes beyond a basic read operation, though it doesn't mention permissions or rate limits.

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 two sentences, front-loaded with the usage trigger, and every sentence adds value (usage context, filtering behavior, output guarantee). No wasted words.

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?

Even with no output schema, the description explains the return shape (text, tier, score, source URL) and notes the coverage_status field. It covers when to use it, what filtering happens, and output context. For a simple read tool without nested objects, this is complete.

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 provides 100% descriptive coverage for all three parameters, so the description is not required to add parameter details. It adds contextual meaning about signal composition (tier, score) but not specific parameter constraints 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 tool retrieves recent harvested signals (text, tier, score, source URL) backing a brand's score, which is a specific verb+resource+scope. Although it doesn't explicitly name sibling tools, the focus on brand signals differentiates it from get_competitive_context and get_momentum_index.

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 opens with 'Use this when an agent needs...' providing explicit context for when to use the tool. It does not explicitly mention alternatives or exclusions, but the guidance is clear enough for the stated purpose.

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 carries the full burden. It discloses useful behaviors: exclusion of scaffold-tier peers and the guarantee that a 'coverage_status' is always present. It also notes the deterministic nature of the one-liner. However, it does not discuss other aspects such as read-only nature, error conditions, or latency, though these are less critical for this type of 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 three sentences with no wasted words. It front-loads the primary use case, then adds the exclusion behavior and the coverage_status guarantee. Every sentence contributes meaningful information, making it an excellent example of conciseness.

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 simple 2-param schema, no output schema, and the tool's read-only nature, the description is quite complete. It covers what the tool returns (competitor set, peer snapshots, one-liner, coverage_status), its key limitation (scaffold tier exclusion), and the deterministic quality. It could go deeper on the shape of the return value, but the 'coverage_status' mention provides crucial context.

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 fully documents both parameters (brand and limit) with clear descriptions, so baseline is 3. The tool's description does not add any additional meaning to the parameters themselves; it focuses on the output and use case rather than parameter usage or interpretation.

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 what the tool provides: a brand's competitor set, peer momentum snapshots, and a deterministic competitive-position one-liner. It also differentiates from siblings by mentioning the unique 'coverage_status' and exclusion of scaffold-tier peers. However, it lacks an explicit verb like 'get' or 'retrieve', instead phrasing it as a use case ('Use this when...'), which is slightly indirect.

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 says 'Use this when an agent needs...', giving clear context for when the tool is appropriate. It also adds a limitation ('Excludes peers without real signal coverage'), which helps in deciding when not to use it. However, it does not mention alternative sibling tools or directly state when to prefer another tool.

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 carries the full burden. It discloses safe read behavior ('Pure read'), determinism, lack of LLM calls, and enumerates the response components, giving the agent a clear behavioral profile. Lacks deeper edge-case details, but sufficient for a read operation.

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; the first front-loads primary use, the second packs return shape and safety traits. Zero filler or redundancy.

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 no output schema, the description adequately summarizes returned fields (composite, four dimensions, tier band, signal count, timestamp) and usage modes. It omits details like limit defaults, but the schema covers those; overall sufficient for an agent to select and invoke the tool.

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 descriptions cover 100% of parameters, so the baseline applies. The description mentions the brand vs. index-top distinction but adds no syntax or semantics beyond the schema; the `limit` parameter is only documented in 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 opens with an explicit 'Use this when...' clause tying the tool to Persimmon's deterministic momentum score for a brand or the index top. It names a specific resource (momentum index) and distinct scope, clearly differentiating from sibling tools focused on raw signals and competitive context.

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?

Provides clear use context ('when an agent needs...') and identifies both invocation modes (specific brand or index top). It doesn't specify exclusions or explicitly name sibling alternatives, but the context makes the choice apparent.

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