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

readOnlyHint=true already tells the agent this is a safe, non-mutating read, so the description carries a lighter burden. It adds nothing about batching limits, partial failure behavior, or auth requirements beyond what annotations and the schema already convey, making 3 the appropriate baseline.

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 tight sentences: the capability and the returned content come first, and the input instruction follows. No filler, though the parenthetical participant enumeration is slightly dense at the cost of skim-ability.

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 usefully enumerates what comes back (participants with name/email/title/internal-vs-external, topics, trackers), which is exactly what the agent needs to know for a detail-fetch tool. The remaining gap is that the 20-ID batch limit and any partial-result behavior are left to the 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?

There is a single parameter with 100% schema description coverage, so the schema fully documents the type and the max-20 constraint. The description only adds provenance ('from list_calls'), which is a small but real supplement over 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?

States a specific verb ('Get detailed info') and resource ('specific Gong calls') and even enumerates the returned sub-fields (participants, topics, trackers). It is clearly distinguishable from list_calls, but it does not explicitly differentiate itself from get_transcripts, which covers a similar call-scoped area.

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?

"Provide call IDs from list_calls" gives workflow guidance on where the required input originates, which is genuinely useful. However, it offers no exclusions or routing guidance versus siblings like get_transcripts or search_calls, so usage is only implied.

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?

readOnlyHint=true already tells the agent this is a safe read, so the description need not restate it. It does add genuine behavioral detail — output is speaker-segmented with timestamps, and speakerId must be joined against parties — but says nothing about transcript availability limits, payload size, or pagination for up to 10 calls.

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, no filler. The retrieval capability is front-loaded and the speakerId join is a compact, high-value second sentence.

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 usefully sketches the return shape (per-speaker segments with timestamps) and explains how to interpret speakerId, which is exactly what the schema cannot convey. It stops short of noting volume/availability caveats for a multi-call batch of transcripts.

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% and there is only one parameter, so the schema already documents callIds and its max-10 constraint. The description adds no syntax, ordering, or ID-format guidance beyond that, so baseline 3 is correct.

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?

Specific verb+resource (retrieve full transcripts for Gong calls) plus an explicit output shape (segmented by speaker with timestamps). It names get_call_details as the companion tool that supplies speaker identity, which separates it from list_calls, search_calls, and get_users.

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 implied usage context by pointing at get_call_details for speakerId resolution, which is a useful workflow hint. However, it never states when to use this tool versus search_calls or list_calls, nor any exclusions (e.g. calls without recordings).

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?

readOnlyHint=true already covers the safety profile, so the remaining burden is low. The description adds that the call returns id, name, email, and title, which is genuinely useful for a no-output-schema tool; it does not mention pagination or result limits, so it falls short of 5.

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 short sentences, zero filler, front-loaded with the identity of the resource and followed immediately by return shape and purpose. Every 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 zero-parameter read-only list tool with no output schema, the description supplies everything needed: what it lists, the fields returned, and why an agent would call it. Nothing required for correct invocation is missing.

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 zero parameters, so there is nothing for the description to clarify and the baseline of 4 applies. The description correctly says nothing extraneous about arguments.

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+resource ("List Gong users") and disambiguates the resource with the parenthetical "company team members." Although the siblings (list_calls, get_call_details, get_transcripts, search_calls) share a call/transcript theme, the user-centric resource is unambiguous, so an agent can route here without opening a 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?

"Use to map speaker IDs in transcripts to people" gives a concrete trigger and even points at the related transcript tools, which is clear usage context. It stops short of any exclusion or explicit when-not guidance, so it doesn't reach the top band.

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 declare readOnlyHint=true, but the description adds real behavioral context beyond that: auto-pagination across Gong's cursor and the shape of the returned data. It stops short of disclosing pagination limits, rate limits, or date-range boundaries.

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 short sentences, no redundancy, with the core purpose and date-range scope front-loaded. Every sentence carries distinct information: purpose, pagination behavior, return fields, and usage routing.

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 usefully enumerates the returned fields (ID, title, start time, duration, direction, URL) and explains pagination, which is exactly what an agent needs. Nothing essential for calling a two-parameter read tool is missing.

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%, with both parameters documented including ISO-8601 format examples, so the schema already does the heavy lifting. The description only restates the date-range framing and adds no new meaning, so the baseline of 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 (List) and resource (calls recorded in Gong) scoped to a date range, which is clear. It does not explicitly distinguish itself from the sibling search_calls, so an agent must infer the boundary between listing and searching.

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?

Gives a concrete usage context: 'Use this to find calls before retrieving transcripts,' routing the agent toward get_transcripts as a follow-up. It does not state when to prefer this over search_calls or when not to use it, so it lacks explicit alternative/exclusion 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?

Annotations only declare readOnlyHint=true, so the description adds real behavioral value: case-insensitive substring matching, the return shape (matching sentences with call context), and the call-scan cap per invocation with remediation advice. It does not mention pagination handling or permission requirements, so it falls short of a 5.

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 tight sentences, front-loaded with the core action, then behavior, then the operational caveat. No filler and 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?

Although no output schema exists, the description covers the return value (matching sentences with call context) and the scan-cap constraint, which are the main things an agent needs. Minor gaps remain around pagination or result limits, but the definition is substantially 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 description coverage is 100% with each parameter documented (keywords, ISO-8601 dates, maxCalls default 50 / hard cap 200). The description adds no syntax or format detail beyond the schema, so the 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?

States a specific verb (search) and resource (Gong call transcripts) with scope (keywords, date range). It is clearly distinguishable from list_calls/get_transcripts in practice, but it never names a sibling or explicitly contrasts its purpose, so it stops short of full sibling differentiation.

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?

Gives one operational guideline - narrow the date range if more calls exist than the scan cap - which implies usage context but does not state when to choose this over get_transcripts or list_calls. Usage is inferred rather than spelled out.

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