Sessy — Amazon SES observability

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is established. The description adds valuable behavioral context beyond annotations: rates are defined as percentages of sends, the optional daily series is noted, and the metric list clarifies exactly what the tool returns. No contradiction exists, and this extra detail helps interpret the output.

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 a single, information-dense sentence that fronts the main purpose and then lists supporting details. Every clause adds value—scope, date range, metric types, and the send-percentage clarification. It avoids fluff and is easy to scan.

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 tool with 0 required parameters, an output schema, and rich annotations, the description covers all essential usage aspects: aggregation behavior, source scoping, date range, metric types, and the optional time series. Edge cases like custom date range constraints are handled by the schema, so the description is complete for the intended complexity.

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 for all 5 parameters is 100%, so the schema carries full semantic weight for parameter details. The description adds minimal parameter-specific meaning (e.g., 'one source or whole account' maps to source_id, 'date range' relates to date_range), but these are restatements of what the schema already documents. Thus the baseline of 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?

The description opens with the specific verb 'Aggregate' and the resource 'email stats', then clarifies scope ('one source or the whole account') and date range. It enumerates the exact metrics (counts, opens/clicks, rates, breakdowns, optional series), making it immediately distinct from sibling tools like search_events or get_message.

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 clearly implies when to use this tool: when the user needs aggregate metrics (counts/rates) across a date range. It gives context about source scope and date presets, but it does not explicitly mention alternatives or exclusions (e.g., 'for individual events use search_events'). This meets 'clear context, no exclusions' rather than the explicit always/never guidance required for a 5.

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?

The description goes well beyond the annotations by disclosing the exact fields returned (subject, sender, destinations, SES tags, event timeline), the 500-event limit, the events_truncated flag, and the recommended paging mechanism. There is no contradiction with the readOnly/idempotent/non-destructive annotations.

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 a single, information-dense sentence that front-loads the core action ('Fetch one email') and packs in field lists, limits, and follow-up guidance. It is efficient but somewhat heavy with parentheticals, which slightly reduces readability.

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?

Together with the annotations (read-only, idempotent) and the presence of an output schema, the description covers the tool's purpose, input provenance, return contents, limits, truncation behavior, and continuation strategy. Nothing important is left unexplained for an agent to invoke this 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?

Schema coverage is 100%, and the parameter description already states 'SES message id from search_events results'. The tool description repeats this same context without adding new syntactic, format, or behavioral details about the parameter, so it adds no incremental value 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 uses a specific verb ('Fetch') and resource ('one email by its ses_message_id'), clearly distinguishing it from sibling tools like search_events (which lists events) and email_stats. It immediately states the exact input needed and the scope of the operation.

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 explicitly says the id comes 'from search_events results' and instructs using search_events to page through additional events, giving clear practical usage context. However, it does not explicitly contrast with email_stats or list_sources, so a small gap remains in alternative 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 already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds valuable context about the 30-day health stats and the tool's role as the entry point, without contradicting the annotations.

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 exactly two sentences, each earning its place: the first defines the output and the second gives actionable workflow guidance. 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?

For a parameterless list tool with an output schema and annotations covering safety, the description fully captures purpose, output contents, and how it fits into the broader workflow. Nothing critical 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 input schema has zero parameters, so there is nothing to explain. Per the rubric, a 0-parameter tool gets a baseline of 4; the description does not need to add parameter details.

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 lists this account's email sources with 30-day health stats (sent count, bounce rate, last event). It also positions itself as the starting point for other tools that take a source_id, effectively distinguishing it from siblings like email_stats, get_message, and search_events.

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?

Explicit workflow guidance is provided: 'Start here: the other tools take a source_id from these results.' This tells the agent to run this tool first to acquire source IDs for subsequent tool calls, making the usage context and alternatives clear.

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?

Beyond the readOnly/idempotent annotations, the description discloses behavioral details such as 'newest first', 'Returns compact rows', and the default date window. These add meaningful context not available from annotations alone, though no mention of pagination or rate limits is made.

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 purposeful and front-loaded. No redundancy; the description is succinct yet packs in scope, ordering, return style, an alternative, and behavioral defaults.

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 9-parameter tool with full schema descriptions and an output schema, the description covers purpose, defaults, and relationships to siblings adequately. It could have mentioned pagination explicitly, but the cursor parameter is documented in the schema, so this is not a major gap.

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 already provides 100% parameter descriptions, but the description enhances understanding of date_range by stating the default (last_30_days) and the all_time option, and clarifies that from_date/to_date are for custom ranges. It also implies the output contains ses_message_id, linking to get_message.

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 searches email events, enumerates the event types, and specifies ordering (newest first). It also distinguishes itself from siblings by pointing to get_message for full timelines and implicitly contrasting with email_stats and list_sources.

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?

Explicitly advises when to use get_message instead: 'use get_message with a row's ses_message_id for the full timeline.' It also clarifies the default date window (last 30 days) and how to override it with date_range 'all_time', giving concrete usage guidance.

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