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 the meaningful behavioral detail that the result is window-scoped and reports which signals have data per service, but says nothing about pagination, empty results, or service identity semantics.

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 tight sentence with no filler, and the scope qualifier ("in the window") is front-loaded. It is slightly terse to the point of being a fragment, but nothing is wasted.

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-optional-parameter read tool with no output schema, the description usefully characterizes the return value (services plus their per-signal data coverage), which is the main thing the agent needs to know. Only minor gaps remain around result size and service naming conventions.

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 both since/until are documented with formats and defaults in the schema itself. The description only echoes the window concept without adding format or interaction detail, so the schema does the heavy lifting and 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 names a specific resource (services) and scopes it to a time window, plus discloses the per-service signal breakdown (metrics, logs, traces). It reads as a noun phrase rather than an explicit verb, but the listing intent is unambiguous and clearly distinct from siblings like new_errors or trace_diff.

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?

There is no statement of when to reach for this tool versus the siblings (new_errors, trace_diff, what_changed), nor any prerequisite or exclusion. The agent must infer that this is the inventory/discovery entry point rather than anything the description states.

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 safety is covered. The description adds real behavioral context beyond that: the dedup rule that messages differing only by IDs count as one error, that each entry carries counts, first-seen time and a redacted example line, and that steady services are also reported. Auth, rate limits and ordering are not disclosed.

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, but front-loaded with the core comparison and then the result contents in priority order; every clause (dedup rule, counts, first-seen, redaction, steady services) carries information. It reads as a run-on, which costs a point, but nothing is padding.

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?

There is no output schema, so the description must carry the return contract — and it does, enumerating the three result groups and the per-entry fields. What is missing is edge behavior: what happens when budget_tokens truncates results, ordering, and the exact shape of 'steady' services versus the rising ones.

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 all five parameters (since, until, service, baseline, budget_tokens) are fully documented in the schema with defaults and formats. The description reinforces the baseline-comparison concept but adds no syntax, units or format detail beyond what the schema already states, 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?

The description names the specific analysis performed (error logs compared against a baseline) and the three result categories: new/spiking errors, services with error volume rising beyond traffic, and steady-error services. It is clearly distinguishable from list_services and trace_diff, though it never names a sibling 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?

Usage is implied by the output framing — an agent can infer this is the tool for spotting newly introduced or regressing errors versus a baseline. However, there is no explicit when-to-use guidance, no statement of when NOT to use it, and no routing against the sibling what_changed, which could plausibly overlap.

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 the safe read-only, idempotent, non-destructive profile, so the bar is low. The description goes beyond them by disclosing the exact result shape (p95 and error rate before/after, per-span latency share, an example trace ID), which is valuable since no output schema exists.

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?

One dense sentence with a front-loaded subject and a colon-delimited list of returned fields; nothing is wasted. It is a noun phrase rather than a verb-first statement, which slightly weakens immediate readability but not materially.

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 carries the return-value burden and does so well, and all six parameters are fully documented in the schema with annotations covering the safety profile. The only real gap is the absence of routing guidance among sibling tools.

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 formats, defaults, and examples. The description only restates the baseline concept and adds no syntax or constraints 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 analysis: span names that regressed in latency or error rate versus a baseline, plus the returned metrics. It clearly identifies the resource (spans) and operation (diff against a baseline), though it never names the siblings it should be preferred over.

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 the phrase 'compared with a baseline' and the regression framing, which tells an agent this is for finding performance/error regressions. However, it offers no explicit when-to-use rules and does not distinguish itself from what_changed or new_errors, which an agent must 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value by disclosing the return structure: a summary paragraph, ranked findings with before/after values and onset times, evidence links, and per-signal coverage.

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 purpose before the return-value detail. The trailing imperative 'Start here.' is a useful orientation cue rather than waste, though it sits at the end rather than the front.

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 carries the burden of describing returns and does so thoroughly (summary, findings, coverage). Combined with fully documented parameters and annotations covering safety, an agent has nearly everything needed, though explicit routing to sibling tools is absent.

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 (since, until, service, baseline, budget_tokens) is already documented in the schema. The description's mention of 'baseline' and '(or all services)' overlaps with what the schema already states, adding no syntax or format detail beyond it.

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 ('what changed in a service... across metrics, logs and traces') and scopes it precisely with the baseline comparison. The 'Start here' framing positions it as the entry-point tool, distinguishing it from the drill-down siblings new_errors and trace_diff.

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?

'Start here' gives clear context that this is the workflow entry point, and 'Omit to scan every service' clarifies scope behavior. It stops short of naming when NOT to use it or routing to new_errors/trace_diff explicitly, so it lacks the full when-not/alternatives treatment of a 5.

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