Context Link

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive behavior, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: the attached widget shows only the source list, not the answer, so the agent must relay the answer text itself. That is practical disclosure beyond the structured fields, though it stops short of describing scoping or result quality behavior.

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: purpose first, then the widget/relay caveat. No filler and each sentence carries information the agent needs.

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 explained, and annotations cover the safety profile. The description covers the critical output-relay gotcha, but omits any mention of restricting retrieval via connection_type/mode or what kind of query text is expected, leaving a small 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?

Schema description coverage is 67%, with 'mode' and 'connection_type' documented in the schema and 'query' undocumented. The description adds no parameter-level meaning at all, so it does not compensate for the undocumented query field; baseline 3 is appropriate given the schema does most of the work.

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: ask a question about the user's connected workspaces and websites, returning a concise answer with citations. It clearly distinguishes the retrieval/Q&A role from memory siblings like get_memory and save_memory, though it never names an alternative tool 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 'ask a question... receive an answer with citations' framing, giving the agent a reasonable sense of when this tool fits. However, there is no guidance on when to prefer this over get_context or get_memory, and no stated conditions or exclusions for using it.

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 (readOnlyHint, idempotentHint, openWorldHint). The description adds genuinely non-obvious behavioral context beyond them: the attached widget shows only the source list, not the retrieved content, so the agent must consume and relay the returned context itself. That is a real UI/side-effect disclosure not present in structured fields.

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, zero padding, and the primary capability is front-loaded before the caveat. Every clause earns its place, including the widget warning.

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 no explanation, and the description covers both the retrieval action and the widget caveat. The remaining gap is routing guidance relative to get_memory/ask_question, which 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 coverage is 67%, and the description adds nothing about mode, query, or connection_type. The undocumented query parameter (0% covered, and required) is not compensated for, but the other two parameters carry adequate schema descriptions, so the baseline 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: retrieve context from the user's connected workspaces and websites. This distinguishes it from get_memory (stored memory) reasonably well, though it never names a sibling explicitly, so the differentiation is inferred rather than stated.

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 useful downstream guidance ('use the returned context to answer the user directly') but never says when to call this versus get_memory or ask_question. The condition for choosing this tool is implied by the term 'context' rather than specified.

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 a closed-world scope, so the safety profile is fully covered without the description. The description adds only the fact that content was "previously saved" and says nothing about behavior when the namespace is missing or how results are returned, so it adds minimal behavioral value beyond the structured fields.

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 the action stated first and the usage condition second; there is no filler, redundancy, or trailing hedging.

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, and for a one-parameter read this definition covers essentially everything an agent needs. The only gap is the absence of any note about behavior on an unknown namespace, a minor omission rather than a blocking one.

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?

With a single parameter at 100% schema description coverage, the schema already explains "namespace" fully. The phrase "by its namespace" in the description merely restates the schema and adds no format, naming-convention, or validation detail beyond it, 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 names a specific verb and resource ("Retrieve previously saved memory content") and the retrieval key ("by its namespace"), so the action is unambiguous. It does not explicitly contrast itself with siblings like save_memory or get_context, but the read/lookup intent is clear.

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 this when the user wants to recall saved content" gives an explicit triggering condition that ties the tool to a user intent. It stops short of stating when NOT to use it or naming get_context as the alternative for context-style retrieval, so it falls just below 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 already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered structurally. The description adds no behavioral detail beyond them — notably it does not warn that reusing a namespace may overwrite an existing memory, which is the key consequence an agent should know. Adds little beyond 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?

Two tight sentences, purpose and usage front-loaded, nothing redundant. Slightly padded by restating 'content' as 'information, notes, or conversation content,' but overall efficient.

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 and full annotation set mean the description needn't explain returns or safety. Purpose and trigger are covered; the only meaningful omission is the destructive/overwrite-on-namespace behavior, which the annotations partially signal.

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 both 'content' and 'namespace' semantics (including the auto-generated timestamped name fallback and dash formatting) are already documented in the schema. The description adds no parameter meaning beyond that, 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 ('Save') and resource ('the user's memory') with the outcome ('for later retrieval'), so it is distinguishable from siblings like get_memory. It does not explicitly name or contrast with any sibling, 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?

Gives clear triggering context: 'Use this when the user wants to save information, notes, or conversation content.' It supplies when-to-use but no when-not or alternative routing (e.g., vs. get_memory or ask_question).

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