SayBriefly

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Read-only' in the description is largely redundant. It does add the useful behavioral context that answers are synthesized from the user's meetings, email, tasks and projects, but says nothing about latency, coverage limits, or answer reliability.

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, front-loaded with the core action and immediately followed by concrete examples. No filler.

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 QA tool with no output schema, the description should ideally say what the response looks like (free-text answer, sources cited, etc.). The data sources are covered but the return shape is left implicit.

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 0% for the single 'question' parameter, so the description must compensate. The parenthetical example questions partially convey the expected natural-language shape and scope, but there is no explicit statement of format, length, or constraints.

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 (ask) and resource (SayBriefly's agent), plus the data sources it draws on (meetings, email, tasks, projects). This is clearly distinguishable from the get/list/search siblings, though it does not name an alternative explicitly.

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 example questions ('what did the client agree last week, what is still open for Acme') which imply when the tool is useful, but gives no explicit when-to-use/when-not guidance or routing versus search_meetings/list_meetings.

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 readOnlyHint, idempotentHint and openWorldHint=false, so the safety and idempotency profile is covered. The description adds the useful detail that transcript retrieval is opt-in via include_transcript, but says nothing about the default result's size, pagination, or performance cost of pulling a full transcript.

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?

Single sentence plus one opt-in clause, front-loaded with the primary purpose and the most important parameter toggle. Nothing is wasteful and the core value proposition leads.

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 tool whose annotations carry the safety profile and whose schema fully documents both params, the description is nearly complete — it explains the returned content and the transcript option. Minor gap: no mention of behavior when meeting_id is invalid or not found.

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 both parameters are fully documented in the schema including the default (false) and the cross-reference to list_meetings for meeting_id. The description restates the include_transcript behavior but adds no format or constraint detail beyond the schema, so 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+resource ('Get one meeting in full') and enumerates what is returned (summary, key decisions, action items, what changed), which distinguishes it from list_meetings and search_meetings. An agent knows exactly what this retrieves 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?

Usage is implied by 'one meeting' with a required meeting_id, positioning it against list_meetings. However, it never explicitly states 'use this when you have a meeting_id' or names alternatives like search_meetings, so guidance remains inferential rather than 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior: results are ordered newest first, and the returned fields (meeting_id, title, date, platform, summary-exists) are disclosed in the absence of an output schema.

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, front-loaded with the core action, then filters, then return shape. No filler and nothing buried.

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, and annotations cover the safety profile. It omits pagination behavior (default/max limit) and any routing versus search_meetings, which are the remaining gaps for a simple list 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 description coverage is 100%, so all four parameters (to, from, limit, title) are already documented in the schema. The description maps loosely onto the filters ('date range or a word in the title') but adds no format or boundary detail beyond that, 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?

States a specific verb and resource (list the user's recorded meetings) plus ordering (newest first), filterability, and return fields. However, it never distinguishes this tool from the sibling search_meetings, and 'filter by a word in the title' sounds like search, so an agent cannot fully disambiguate the two from the description alone.

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 implied: when you want recorded meetings, optionally narrowed by date range or title text. There is no explicit when-to-use/when-not guidance and no mention of the sibling search_meetings, which overlaps heavily with the described filtering behavior.

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 readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by defining scope (only the user's own items in their workspace) and enumerating the returned fields, which matters since there is no output schema. It does not mention ordering or result caps, but the schema covers the cap.

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 sentences, each doing distinct work: scope, usage triggers, and return shape. It is front-loaded on what the tool returns and wastes no 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?

With no output schema, the description usefully enumerates the returned fields (id, title, status, due date, priority, project, source) and pins down the scope, which is what an agent needs to interpret results. Minor omissions like ordering or total-count behavior are the only remaining gaps.

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 every parameter is already documented with defaults, max values and date format. The description only loosely echoes project and due-date filtering ('due this week', 'project X') without adding syntax or semantics 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?

The description states a specific verb and resource ('List the user's to-dos') and immediately scopes them ('their own items in their workspace'), so an agent knows exactly what dataset comes back. The sibling tools are all meeting-related, so no todo-sibling differentiation is required, but the phrasing would still distinguish it cleanly.

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 concrete trigger phrases — 'what is on my plate', 'what is due this week', 'open tasks for project X' — which map well onto real user intents. It stops short of explicit when-not-to-use guidance or naming an alternative tool, which is the only gap.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds one genuinely new behavioral fact – that results include the exact matching lines – but says nothing about matching semantics (exact vs fuzzy, case sensitivity) or result ordering/truncation.

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 core capability is front-loaded and the return nature follows immediately. 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 two-parameter read tool with no output schema, the description covers what it does and roughly what comes back (matching meetings with exact lines). It stops short of describing result shape or the default limit behavior beyond what the schema already states.

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, but the description adds real meaning the schema lacks: it clarifies that 'query' is matched against both spoken transcript content and summary text, not just a generic string field.

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 (find/search) and resource (meetings) plus the searchable scope: spoken words or summary text. It never names a sibling such as list_meetings or get_meeting, so the agent must infer the boundary from the verb alone.

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: 'where a word or phrase was said' suggests content-based retrieval as opposed to browsing, but there is no explicit when-to-use, when-not-to-use, or pointer to list_meetings/get_meeting as alternatives.

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