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

With no annotations, the description carries the full behavioral burden, and it discloses almost nothing: not whether the brief is persisted or ephemeral, whether generation is costly/slow, what auth or harness access is required, or whether output is deterministic. The one useful signal is that it synthesizes rather than fetches, which is inferable from 'Generate'.

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 sentence that front-loads the verb and the artifact, then parenthetically enumerates the brief's sections. Zero filler and no restatement of the tool name.

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?

An output schema exists, so return shape is covered and need not be described. But for a tool with a required, entirely undefined parameter and no annotations, the description leaves critical invocation information 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 description coverage is 0%, so the description must compensate, and it largely does not. 'For a session' loosely implies session_id (whose 'latest' default lives only in the schema), but source_harness — a REQUIRED parameter — is given no meaning anywhere, leaving the agent unable to supply it correctly.

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 ('Generate') and a concrete artifact ('executive handoff brief') with its contents enumerated (goal, files, blocker, next steps) and its scope ('for a session'). This clearly separates it from the list/inspect/search siblings, which retrieve rather than synthesize. It stops short of naming any sibling explicitly, so 4 rather than 5.

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?

No statement of when to prefer this over inspect_session or list_recent_sessions, and no prerequisites or exclusions. 'For a session' is the only contextual hint, and it is too thin to count as 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?

No annotations are provided, so the description carries the full burden. "Read" implies a non-mutating operation and "ordered" conveys result sequencing, but nothing is said about permissions, truncation, how much history is returned, or what happens when a session_id doesn't exist.

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 with zero filler, and the core purpose is front-loaded ahead of the default-value note. It is tight, though it spends one of its two sentences on a detail the schema already encodes as a default.

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?

An output schema exists, so return-value detail is not required, but the tool has a required `harness` parameter that is undocumented in both description and schema, and with no annotations the safety/behavior profile is unstated. For a three-parameter read tool this is insufficient.

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%, yet the description only clarifies session_id (defaults to the newest session). The required `harness` parameter is never explained anywhere, and max_turns/default 10 is left entirely to the schema, so a critical gap remains.

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 a well-defined resource (a session's ordered conversation and tool events), which is enough to separate it from list_recent_sessions and search_sessions_history. It stops short of explicitly naming how it differs from those siblings, so it is clear but not fully differentiated.

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 guidance on when to inspect a session versus listing recent sessions or searching history; the agent must infer that from the verb "Read." No prerequisites, exclusions, or alternative tools are mentioned.

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?

With no annotations, the description carries the full burden. It discloses ordering (newest first) and the harness domain, which is genuine behavioral context, but says nothing about permissions, pagination/truncation, or what a limited result set implies.

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 compact sentence with the action, scope and ordering front-loaded. Nothing is padded or restated.

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?

An output schema exists, so return values need not be described. For a simple two-param list tool, the description covers scope, ordering and the harness domain adequately; the unexplained 'limit' and the lack of sibling routing are the only real 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 0% for two parameters. The description compensates partially by enumerating valid harness values (codex, claude, antigravity, opencode, freebuff), which the schema lacks as an enum, but it never explains the 'limit' parameter or its default of 5.

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 recent sessions'), plus scope ('recent'), domain ('across harnesses' with five named values) and ordering ('newest first'). It does not distinguish itself from siblings like search_sessions_history or list-style alternatives, so it stops short of a 5.

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 word 'recent' and 'newest first' imply the browsing use case, but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent must infer whether this or search_sessions_history is the right entry point.

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 are absent, so the description carries the full behavioral burden. It implies a read-only search but says nothing about matching semantics (substring, case sensitivity, tokenization), pagination, ordering, or result volume, which matter for a limit-bearing search tool.

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 no padding or repetition. It is efficient, though its brevity contributes to the gaps noted in other dimensions.

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?

The output schema covers return values, but for a three-parameter search tool with zero schema descriptions and no annotations, the description omits usage routing and parameter meaning. It is under-specified relative to the tool's 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 description coverage is 0%, so the description must compensate, and it largely does not. 'One or every harness' hints that harness is optional/null, but query and limit (default 10) semantics are left entirely unexplained.

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: keyword search over session message texts, with the scope of one or every harness. It is clear what the tool does, but it never names or contrasts with siblings like list_recent_sessions, which also surfaces sessions.

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?

No when-to-use guidance is given. It is not stated whether this is the right tool when you already know a session id (inspect_session) or want recency rather than keyword matching (list_recent_sessions); the agent must infer that from the name alone.

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