SignalShelf

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

Adds substantial context beyond the annotations: all inputs are validated before any fetch happens, results are returned per item with individual errors, processing is sequential, and the credit model charges one credit only for a fresh live success while demos, cache hits, and failures are free. That is exactly the kind of cost/failure semantics an agent needs before committing to a call, none of which the readOnlyHint/openWorldHint flags 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?

Four tight sentences with no filler, but the ordering is slightly off: it opens with the validation precondition rather than the core action, and the reader must infer the operation from 'fetching.' Still, each sentence carries distinct, non-redundant 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?

With no output schema, the description covers the shape of the response at a high level ('per-item successes/errors') and covers the cost and ordering semantics, which is enough to call it correctly. It leaves the exact error object shape and whether partial successes still cost credits fully explicit only for the live-success case.

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 baseline is 3, but the description adds real meaning by tying the mode and freshness fields to billing: a 'live' fresh item costs a credit, demo and cache hits are free. 'Processed sequentially' combined with max ten also clarifies that per-item errors do not abort the run, which the schema alone does not express.

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 title plus phrases like 'before fetching any' and 'per-item successes/errors' make clear this is a batched profile fetch of up to ten items. It is distinguishable from the singular sibling via the ten-item cap and per-item results, though the description itself never plainly states 'looks up public profiles' — that verb+resource lives in the title rather than the description body.

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?

Batch usage is implied by 'Maximum ten items' and the per-item cost model, and the zero-cost demo path nudges toward non-live usage. However, there is no explicit 'use this instead of signalshelf_profile when you have multiple handles' guidance, and no stated prerequisite (e.g., credits or auth) for choosing it over the single-profile sibling.

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 already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description adds genuinely useful context beyond them: 'No source fetches and zero credits,' which tells the agent this call is free and side-effect-free, plus what the response contains (parameter schemas and credit prices).

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?

A single dense sentence with the core action front-loaded, followed by the filtering behavior and the cost guarantee. No 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?

Although there is no output schema, the description explains what is returned (matching operations with full parameter schemas and credit prices, or a compact index). Combined with the annotations, an agent has everything needed to call it 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?

Schema coverage is 100%, so the baseline is 3. The description goes further by explaining the semantic effect of the optional parameters: query and platform narrow results, while no filters yields a compact index, which is behavior the schema alone does not convey.

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 ('Search SignalShelf operations') and quantifies scope (~250 across named platforms). It is clearly distinguishable from siblings like signalshelf_credits or signalshelf_batch, which are not search tools.

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?

Explains the two filtering modes: pass query and/or platform for matches, or omit filters for a compact index. It does not explicitly say this is the discovery step before invoking other operations, but the context is clear enough for an agent to infer.

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 already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful data-minimization context ('No other account details or API keys are returned'), but the fragment 'Zero credits.' is ambiguous — it could mean the call costs nothing, the balance is zero, or credits are not the return type — which undercuts clarity rather than adding to it.

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 short and front-loads the core action, which is good. However, the two-word fragment 'Zero credits.' is structural noise whose meaning an agent cannot reliably resolve, so not every sentence clearly 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 zero-parameter read with complete annotations, the description covers who the data belongs to and what is not returned. With no output schema, it could say more about the return shape (a scalar balance versus an object), but the gap is minor for this complexity level.

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 tool takes no parameters, so there is nothing for the description to disambiguate; the empty schema with additionalProperties=false is self-explanatory. Baseline 4 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 ('Read') and resource ('the authenticated account's current database balance'), scoped to the caller's own account. It stops short of naming a sibling, though the clause 'No other account details' implicitly separates it from signalshelf_profile.

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 is only implied: an agent can infer this is the balance lookup, and the exclusion of account details hints that signalshelf_profile covers the rest. There is no explicit when-to-use or when-not-to-use statement, and no sibling is 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?

Annotations cover the safety profile (readOnlyHint false, destructiveHint false, openWorldHint true, idempotentHint false), and the description adds genuinely non-obvious behavior: the credit is charged only on a successful fresh fetch, while cache hits and failures cost zero. It also warns that public-page engines can be blocked or incomplete, which sets expectations for partial or missing results. It stops short of saying how a block or failure is surfaced to the caller, for example as an error or as partial data.

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?

Three compact sentences open with the most important information: what is returned, then the cost model, then the reliability caveat. Each sentence carries distinct information with no filler, although the mode-economics sentence duplicates guidance already present in the schema.

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 output schema, the description responsibly notes that the return includes cache/cost metadata alongside the profile, and it covers cost and reliability for a network-backed tool with a charged mode. It leaves the profile payload shape loosely defined as 'normalized' and says nothing about rate limits or per-call concurrency, which keeps it from being fully 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?

Schema coverage is 100%, so all four parameters, including the mode and freshness enums, are already documented in the schema with defaults. The description restates the demo-is-free and live-costs model but adds no syntax or behavioral detail beyond what the schema fields already say. That lands at the baseline for fully documented parameters.

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 specific verb and resource: return a normalized public profile plus cache/cost metadata, which tells an agent exactly what it gets back. It never names a sibling, though, so an agent must infer on its own that signalshelf_batch is the multi-profile variant and signalshelf_resource is a different resource type.

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 clear guidance for the key decision of demo versus live, calling demo illustrative and free and noting that live charges a credit only on a successful fresh fetch. It offers no explicit exclusions or routing advice toward sibling tools, so the guidance is strong on mode choice but silent on tool choice.

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 flag openWorldHint=true, destructiveHint=false, idempotentHint=false and readOnlyHint=false; the description adds the substantive context those flags lack — that this is live public data, that a fresh success costs the operation's credits (1, or 2+ for heavier ops), and that accepted cache hits and failures cost zero, which also explains the non-readonly annotation. It does not discuss rate limits, auth, or error payloads, so it is strong but not exhaustive.

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 cost model and the capabilities dependency are front-loaded and dense with useful information, with no filler sentences. The long platform enumeration ('TikTok, Instagram, Threads, Facebook, X, LinkedIn...') is partly redundant with the platform enum in the schema and is the one stretch that could be trimmed.

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 generic dispatcher tool with a nested free-form params object and no output schema, the description covers what an agent needs to call it correctly: how to obtain valid platform/resource values, how params bind to the operation schema, and the credit consequences of a call. It leaves the response payload shape and failure semantics largely unexplained, which matters somewhat given there is no output schema.

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 schema already documents platform, resource, params and freshness in detail. The description adds cross-field meaning — params are keyed to the selected operation's schema rather than to this tool's own schema — but otherwise repeats the schema's guidance, which is the baseline-3 case.

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 ('Fetch any implemented public resource') and immediately ties it to the discovery sibling 'signalshelf_capabilities', showing the exact key format (platform "web", resource = "tiktok/video/comments"). The platform list makes the scope concrete enough that an agent can distinguish it from signalshelf_batch and signalshelf_capabilities without opening any schema.

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 establishes a clear prerequisite workflow: the resource must be one returned by signalshelf_capabilities, and params must match that operation's schema. It does not explicitly say when to prefer signalshelf_batch instead of calling this repeatedly, so the alternative-routing guidance is implied rather than stated.

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 already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the response is redacted (no source payloads, account IDs, or secrets) and the call costs zero credits — both are facts an agent cannot get from the annotation block.

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?

A single front-loaded sentence with the scope, the cap, the redaction guarantee, and the cost signal — no filler or repetition of the name or title.

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 one-parameter read tool with full annotations, the definition covers scope, limits, and what is withheld. With no output schema, it could say more about what an event record actually contains (timestamps, query text, etc.), but the essentials for correct invocation are present.

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% and the single 'limit' parameter is fully documented with range and default. The description only echoes the upper bound of 100, adding no syntax or format detail beyond the schema, so the 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 ('Read') and resource ('recent lookup events') scoped to 'the authenticated account', with an explicit cap of 100. It doesn't name a sibling to contrast with, but the resource is concrete enough that an agent can separate it from signalshelf_profile or signalshelf_credits.

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 is only implied by the verb and the 'Zero credits' note, which hints this is a free alternative to credit-costing lookups. There is no explicit when-to-use, when-not-to-use, or named alternative among the siblings.

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